© 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. 107616
    Prev
    Next
    INDEX
    Explanations

    coding variable assignments

    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
    in
    -1.07
    z
    -1.02
    n
    -1.02
    u
    -1.00
    b
    -0.97
    w
    -0.97
    j
    -0.93
    as
    -0.92
    x
    -0.92
    al
    -0.90
    POSITIVE LOGITS
    jando
    1.10
    킁
    0.98
    瞜
    0.97
    ichtete
    0.93
     лесу
    0.91
     nuage
    0.91
    小米
    0.90
     moule
    0.89
    を買う
    0.88
     déjà
    0.88
    Activations Density 0.099%

    No Known Activations