© 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. 34-GEMMASCOPE-RES-131K
    7. 31411
    Prev
    Next
    INDEX
    Explanations

    chromosome deletions

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

    text formatting elements like dates, numbers, or technical notation in documentation or references.

    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
    ὲν
    -0.92
     their
    -0.90
    jería
    -0.88
    婦人
    -0.88
     alkoh
    -0.87
    postsleuth
    -0.84
    marshall
    -0.83
     svoj
    -0.81
     THEIR
    -0.81
     timmar
    -0.81
    POSITIVE LOGITS
     a
    1.69
     javax
    1.18
     amongst
    1.05
    private
    1.00
     among
    0.94
     отказа
    0.90
    among
    0.87
     –
    0.84
     =
    0.84
     Einzelnen
    0.83
    Activations Density 0.000%

    No Known Activations