© 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. 22-GEMMASCOPE-RES-131K
    7. 27565
    Prev
    Next
    INDEX
    Explanations

    equivalent or mapping

    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
    ごとの
    -0.91
     pequ
    -0.89
     coute
    -0.88
     pione
    -0.84
    サンド
    -0.84
    おそ
    -0.83
    ほら
    -0.83
     crea
    -0.82
    を選択
    -0.82
     шокола
    -0.82
    POSITIVE LOGITS
     corresponds
    1.06
     vervangen
    1.00
    Equivalent
    0.91
     now
    0.91
     instead
    0.91
     correspond
    0.91
    Become
    0.90
     replaced
    0.90
     analogues
    0.89
    相当
    0.88
    Activations Density 0.049%

    No Known Activations