© 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. 72086
    Prev
    Next
    INDEX
    Explanations

    language, translation, or grammatical form

    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
    つづく
    -1.19
    為に
    -1.13
    postolic
    -1.10
    ViewChild
    -1.05
    必要があります
    -1.02
     such
    -1.02
    ごとの
    -1.02
     the
    -0.98
    ところに
    -0.97
     \%}$
    -0.96
    POSITIVE LOGITS
    Pengertian
    1.09
    <bos>
    1.09
    など
    1.08
    は
    1.06
    Preparazione
    1.06
    や
    1.05
    Penjelasan
    1.04
    だから
    1.03
    Mengapa
    1.02
    Zubereitung
    0.99
    Activations Density 0.045%

    No Known Activations