© 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. 108468
    Prev
    Next
    INDEX
    Explanations

    math expressions and code

    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
     geograf
    -0.88
     уж
    -0.88
    chenken
    -0.84
    ̦
    -0.82
    setdefault
    -0.82
    UNUSED
    -0.82
    úrate
    -0.79
    triangleright
    -0.79
     felipe
    -0.78
    resave
    -0.78
    POSITIVE LOGITS
     proberen
    1.03
    は約
    0.98
     simplemente
    0.97
     versucht
    0.93
     atraer
    0.92
    辄
    0.92
    $,
    0.91
     tentar
    0.91
     simplesmente
    0.91
    }$,
    0.89
    Activations Density 0.001%

    No Known Activations