© 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. 12397
    Prev
    Next
    INDEX
    Explanations

    reasons or justifications for actions

    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
     Mijn
    -1.28
     данной
    -1.22
    Från
    -1.10
    jours
    -1.10
    Detta
    -1.09
    𝔇
    -1.09
    𝐼
    -1.07
    ༴
    -1.06
    ︱
    -1.05
     prenn
    -1.05
    POSITIVE LOGITS
     or
    1.32
    <bos>
    1.28
     in
    1.27
    8
    1.20
     
    1.13
     to
    1.13
    *
    1.13
    ness
    1.12
    などを
    1.10
    2
    1.09
    Activations Density 0.032%

    No Known Activations