Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8704
    Prev
    Next
    INDEX
    Explanations

    file extensions

    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
     both
    -1.40
     their
    -1.39
     two
    -1.20
     just
    -1.16
     not
    -1.16
     all
    -1.14
     large
    -1.14
     our
    -1.13
     various
    -1.13
     three
    -1.10
    POSITIVE LOGITS
     delightfully
    1.12
     déchets
    1.09
    轳
    1.09
     capacités
    1.08
    艄
    1.05
     symptômes
    1.05
     panneaux
    1.02
    HANG
    1.02
     produrre
    1.02
     ส์
    1.02
    Activations Density 0.034%

    No Known Activations