© 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. 22-GEMMASCOPE-RES-131K
    7. 128889
    Prev
    Next
    INDEX
    Explanations

    configuration file path

    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_22/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
    ↵↵
    -1.01
    这条
    -0.99
    另一种
    -0.98
     😭
    -0.97
     🔥🔥
    -0.94
    <b>
    -0.93
    _
    -0.93
    sodik
    -0.92
    ↵
    -0.91
     kuto
    -0.91
    POSITIVE LOGITS
     our
    1.44
     nuestro
    1.23
     opravdu
    1.14
     náš
    1.13
     خواهیم
    1.11
    ⩩
    1.08
     nuestra
    1.06
     което
    1.06
    Médaille
    1.02
    iniques
    1.02
    Activations Density 0.072%

    No Known Activations