© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49557
    Prev
    Next
    INDEX
    Explanations

    Poor Urban, Mystikal album

    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
     Enkel
    -0.85
    礡
    -0.85
    İZ
    -0.81
     different
    -0.79
    paul
    -0.78
    bigr
    -0.77
    UCION
    -0.77
    པ་
    -0.76
    dung
    -0.76
    IMIENTO
    -0.74
    POSITIVE LOGITS
    highlighted
    0.88
    MLP
    0.85
     meccan
    0.85
     DKI
    0.82
     alrededores
    0.81
    if
    0.79
     throats
    0.79
     Harlan
    0.77
    似乎
    0.76
     strikingly
    0.76
    Activations Density 0.013%

    No Known Activations