© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31958
    Prev
    Next
    INDEX
    Explanations

    functional analysis or inhibition

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

    Unicode escape sequences like \uXXXX or \xXX that represent special characters.

    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
     still
    -0.83
     ingrediente
    -0.80
     Palermo
    -0.79
     Pis
    -0.75
     Leggings
    -0.75
     classifica
    -0.74
     adorno
    -0.73
    داية
    -0.72
     blasted
    -0.72
    énage
    -0.72
    POSITIVE LOGITS
    ennium
    0.93
    要想
    0.87
     kvě
    0.82
    ܇
    0.82
     MAKES
    0.82
     більше
    0.82
     BFF
    0.81
    celand
    0.80
    ัส
    0.80
     SNL
    0.80
    Activations Density 0.008%

    No Known Activations