© 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. 10846
    Prev
    Next
    INDEX
    Explanations

    What after question word

    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
     ſeveral
    -1.23
     Cette
    -1.16
    ⻑
    -1.13
     También
    -1.12
     également
    -1.10
    さび
    -1.09
     também
    -1.09
     descri
    -1.06
    那种
    -1.05
     skil
    -1.05
    POSITIVE LOGITS
     from
    1.30
     because
    1.28
     in
    1.21
     by
    1.20
     first
    1.13
     on
    1.13
     Both
    1.13
     really
    1.12
     extraordinarily
    1.10
     ALWAYS
    1.09
    Activations Density 0.007%

    No Known Activations