© 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. 10-GEMMASCOPE-RES-131K
    7. 14292
    Prev
    Next
    INDEX
    Explanations

    magnified endoscopic features

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

    opening curly braces followed by code block indentation in programming languages.

    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_10/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
    8
    -2.03
    7
    -2.03
    3
    -2.02
    5
    -1.91
    2
    -1.89
    6
    -1.80
    走吧
    -1.80
    on
    -1.74
    j
    -1.73
    d
    -1.71
    POSITIVE LOGITS
     Organizador
    1.77
     When
    1.67
     memperoleh
    1.61
    When
    1.55
     ANYTHING
    1.51
     Cancelar
    1.51
    .
    1.48
    鸸
    1.48
     сделали
    1.48
     Niemand
    1.45
    Activations Density 0.000%

    No Known Activations