© 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. 54087
    Prev
    Next
    INDEX
    Explanations

    You can

    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
    </b>
    -1.12
     is
    -1.08
    </em>
    -1.06
     rossa
    -1.05
    んでいます
    -1.05
     zucca
    -1.04
     citta
    -1.03
     used
    -1.02
     gril
    -1.01
     firma
    -1.00
    POSITIVE LOGITS
     can
    1.69
    に入れる
    1.61
     podían
    1.55
     azonban
    1.55
     PUEDE
    1.45
     verwijzen
    1.42
     pouvez
    1.39
     vertrouwen
    1.30
    に入れ
    1.30
     plezier
    1.29
    Activations Density 0.135%

    No Known Activations