© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26382
    Prev
    Next
    INDEX
    Explanations

    sessions, liked, useful

    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
     if
    -1.44
    When
    -1.33
     memili
    -1.28
     menurun
    -1.26
    ditionally
    -1.24
    roud
    -1.22
    Since
    -1.20
     Légion
    -1.20
     sepen
    -1.18
     minne
    -1.17
    POSITIVE LOGITS
     learning
    1.46
    又能
    1.41
     บาง
    1.31
     便利
    1.30
     genoc
    1.30
     ถูก
    1.28
    又被
    1.28
     useful
    1.28
     was
    1.24
     learn
    1.24
    Activations Density 0.017%

    No Known Activations