© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 223735
    Prev
    Next
    INDEX
    Explanations

    cell and pounds

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

    mapping lost things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    дә
    0.58
    ะ
    0.52
    ای
    0.50
    ਵਾ
    0.50
    ਰੀ
    0.48
    </
    0.47
    ску
    0.46
    ատ
    0.45
    IF
    0.45
    для
    0.44
    POSITIVE LOGITS
     Website
    0.48
    jom
    0.47
    HeaderText
    0.46
     website
    0.45
     Gori
    0.45
    眦
    0.45
    Website
    0.45
     виправи
    0.43
     menschen
    0.42
     prolifer
    0.42
    Activations Density 0.000%

    No Known Activations