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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110637
    Prev
    Next
    INDEX
    Explanations

    dates and email addresses

    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_34/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
     for
    -1.45
     from
    -1.28
     in
    -1.27
     with
    -1.26
     one
    -1.23
     before
    -1.18
     after
    -1.17
     as
    -1.16
     also
    -1.14
     such
    -1.14
    POSITIVE LOGITS
     plafon
    1.12
     éte
    1.11
     inond
    1.09
     ambassade
    1.09
     éché
    1.07
    廪
    1.07
     remé
    1.06
     rembourse
    1.06
     goû
    1.05
     れる
    1.04
    Activations Density 0.018%

    No Known Activations