© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 487
    Prev
    Next
    INDEX
    Explanations

    don't know what or how

    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
     télécharge
    -1.21
     traductions
    -1.16
     ネック
    -1.11
     素描
    -1.09
     gustado
    -1.06
    やっぱり
    -1.06
     algun
    -1.06
     totul
    -1.05
    paravant
    -1.05
     vada
    -1.05
    POSITIVE LOGITS
     or
    2.34
     how
    2.05
     nor
    1.97
     until
    1.88
     even
    1.61
     any
    1.60
     what
    1.60
     except
    1.53
     but
    1.49
     many
    1.49
    Activations Density 0.052%

    No Known Activations