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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129461
    Prev
    Next
    INDEX
    Explanations

    life stages and relationships

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

    personification of objects or concepts where they are described with human-like qualities or behaviors.

    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_22/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
    IFESTYLE
    -1.05
    といって
    -1.00
    と言って
    -0.99
     Partager
    -0.98
     twar
    -0.97
     γυναι
    -0.96
     Ajoutez
    -0.96
     subsided
    -0.96
     Logement
    -0.95
     контроля
    -0.94
    POSITIVE LOGITS
     its
    1.63
    tiest
    1.10
    служи
    1.10
    它
    1.08
     пациента
    1.06
    Its
    1.02
     Oblast
    0.96
    usd
    0.96
    they
    0.94
    是被
    0.93
    Activations Density 0.109%

    No Known Activations