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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8086
    Prev
    Next
    INDEX
    Explanations

    technical compound phrases

    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
    スポンサーリンク
    -1.35
    さぁ
    -1.34
    我が家の
    -1.19
    さてさて
    -1.17
    さあ
    -1.17
    おしゃれ
    -1.16
    に行きました
    -1.12
    夏休み
    -1.11
    得太
    -1.11
    ကိုးက
    -1.11
    POSITIVE LOGITS
     counterpart
    1.43
     counterparts
    1.32
     or
    1.16
     fleste
    1.09
     یا
    1.08
     another
    1.08
    hoho
    1.01
    CCIÓN
    1.00
     alternativas
    1.00
    或
    1.00
    Activations Density 0.280%

    No Known Activations