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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40344
    Prev
    Next
    INDEX
    Explanations

    status of offerings and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Tuber
    -1.25
    šené
    -1.18
     laranja
    -1.17
    carus
    -1.14
     />';
    -1.11
    itets
    -1.09
    elts
    -1.06
    efit
    -1.05
    既然
    -1.04
    今天
    -1.03
    POSITIVE LOGITS
     will
    2.59
     is
    2.27
     can
    1.97
     may
    1.51
     should
    1.51
     cannot
    1.48
     are
    1.44
     must
    1.33
    は
    1.22
     only
    1.20
    Activations Density 0.055%

    No Known Activations