© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128751
    Prev
    Next
    INDEX
    Explanations

    the aim of the study

    np_acts-logits-general · gemini-2.5-flash-lite

    the phrase "The aim(s) of this study was/were to" in academic paper abstracts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron fires on expressions of a paper’s research objectives (e.g., “The aim(s) of this study …”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cráneo
    -2.27
    %;
    
    -2.23
    rxjs
    -2.19
     reservados
    -2.19
    木製
    -2.17
    ဴ
    -2.14
    "}}>
    -2.11
    </tfoot>
    -2.09
    **
    -2.05
    %">
    -2.03
    POSITIVE LOGITS
    1
    2.98
    ↵↵
    2.59
    h
    2.41
    y
    2.41
    s
    2.38
    at
    2.31
            
    2.31
    4
    2.30
    o
    2.22
          
    2.20
    Activations Density 0.050%

    No Known Activations