© 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. 30431
    Prev
    Next
    INDEX
    Explanations

    Denver Premium Outlets

    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
     GetData
    -0.71
     Jangan
    -0.67
    **********
    -0.66
     十
    -0.66
    SignUp
    -0.66
     دست
    -0.65
     guber
    -0.65
     {%
    -0.65
    Филь
    -0.65
    ilidade
    -0.64
    POSITIVE LOGITS
    <()>
    0.71
    givings
    0.70
    стрі
    0.69
    也算是
    0.69
    lore
    0.68
     Aufführung
    0.68
    addProperty
    0.68
     bParam
    0.67
     Alumni
    0.66
    EnumMember
    0.66
    Activations Density 0.067%

    No Known Activations