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. 8672
    Prev
    Next
    INDEX
    Explanations

    biological context descriptions

    np_acts-logits-general · gemini-2.5-flash-lite

    text in non-English languages, particularly in technical or academic content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     nơi
    -1.11
     końca
    -1.04
     siempre
    -1.01
     toujours
    -1.01
    also
    -0.99
    フル
    -0.98
    >
    -0.97
     into
    -0.96
    '
    -0.94
     also
    -0.91
    POSITIVE LOGITS
     đó
    1.20
     when
    1.16
     while
    1.13
    นั้น
    1.08
     this
    1.06
     realizzata
    1.05
     embra
    1.02
    ときに
    1.02
    يور
    0.99
    ܜ
    0.97
    Activations Density 0.000%

    No Known Activations