© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106218
    Prev
    Next
    INDEX
    Explanations

    keys and code identifiers

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

    The neuron fires on occurrences of the “@” symbol (e.g. annotations or instance‐variable prefixes in code).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    licopter
    -1.53
     gyak
    -1.42
    achieve
    -1.41
    announced
    -1.41
     zobaczyć
    -1.38
    wouldn
    -1.38
     ACCIDENT
    -1.37
     Posteriormente
    -1.35
    pergillus
    -1.35
     renfor
    -1.33
    POSITIVE LOGITS
    8
    1.32
    9
    1.26
    3
    1.21
    6
    1.17
     ,
    1.16
    5
    1.13
    4
    1.13
     classific
    1.12
     only
    1.10
     entire
    1.09
    Activations Density 0.032%

    No Known Activations