© 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. 72379
    Prev
    Next
    INDEX
    Explanations

    Editing Style, KeyDown (, Posts Tagged, Antibody responses

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

    Android programming method names and event handlers related to user interface.

    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
     cierta
    -1.05
    
    -1.00
    paigns
    -0.99
     verhind
    -0.98
     downloaden
    -0.96
    kasten
    -0.96
    z
    -0.96
     certaines
    -0.94
    it
    -0.93
    прият
    -0.91
    POSITIVE LOGITS
     menu
    1.23
    símbolo
    1.03
    埜
    1.02
    niño
    0.99
     lära
    0.99
    ള്ള
    0.99
     verduras
    0.99
    leggings
    0.98
     homen
    0.98
    化した
    0.98
    Activations Density 0.000%

    No Known Activations