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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118962
    Prev
    Next
    INDEX
    Explanations

    and so on / so forth

    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_34/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
     hb
    -0.95
     trampa
    -0.92
    mployment
    -0.91
    σετε
    -0.91
     sae
    -0.90
     borboleta
    -0.89
     ttc
    -0.89
    𝗐
    -0.89
    :-(
    -0.89
    Abp
    -0.88
    POSITIVE LOGITS
     on
    2.48
     forth
    1.88
     it
    1.25
     did
    1.03
    &
    0.93
    ?
    0.93
     are
    0.92
     was
    0.91
     were
    0.91
     son
    0.91
    Activations Density 0.005%

    No Known Activations