© 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. 34-GEMMASCOPE-RES-131K
    7. 93801
    Prev
    Next
    INDEX
    Explanations

    explaining a situation or problem

    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
     autonomie
    -1.34
    rably
    -1.27
     FBref
    -1.23
     militari
    -1.20
    essentially
    -1.17
     GeoNames
    -1.16
     zoude
    -1.14
    dată
    -1.13
    
    -1.12
     ?";
    -1.11
    POSITIVE LOGITS
     because
    3.53
     due
    2.69
     just
    2.14
     that
    2.06
     from
    2.03
    Because
    1.70
     Because
    1.68
     related
    1.66
     karena
    1.60
    because
    1.60
    Activations Density 0.047%

    No Known Activations