© 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. 118703
    Prev
    Next
    INDEX
    Explanations

    forming verbs and states

    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
    也就是说
    -0.87
    チーフ
    -0.77
    ampe
    -0.75
    Према
    -0.73
     revisar
    -0.69
    Sinopse
    -0.67
    Him
    -0.66
    ノコ
    -0.66
     elimination
    -0.66
    holes
    -0.66
    POSITIVE LOGITS
    ening
    3.59
    ened
    3.19
    ENING
    2.13
    ener
    1.66
    ENED
    1.60
    eners
    1.48
    ens
    1.40
    ning
    1.35
    tening
    1.31
    ニング
    1.20
    Activations Density 0.040%

    No Known Activations