© 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. 3041
    Prev
    Next
    INDEX
    Explanations

    content descriptions and reactions

    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
     noticeably
    -0.92
     страте
    -0.90
    Strateg
    -0.87
     “
    -0.85
     favorably
    -0.84
     notable
    -0.82
     several
    -0.82
    aerop
    -0.81
    tesla
    -0.81
     захворю
    -0.80
    POSITIVE LOGITS
    Reaction
    1.11
    reaction
    1.11
     reaction
    1.10
     Reaction
    1.03
     your
    1.03
     compromisos
    0.96
    我们
    0.96
    NameExpr
    0.92
    riched
    0.91
    
    0.91
    Activations Density 0.036%

    No Known Activations