© 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. 122694
    Prev
    Next
    INDEX
    Explanations

    method of claim

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

    ladder safety

    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
    wier
    0.45
     সাজেশন
    0.43
    ul
    0.43
     포인트
    0.43
    c
    0.42
    attack
    0.41
     واحدة
    0.41
    faithful
    0.40
    ulf
    0.40
     אותו
    0.40
    POSITIVE LOGITS
    летов
    0.50
    .|__
    0.47
     contempl
    0.46
    рий
    0.46
    会社の
    0.44
    桢
    0.44
    ૈ
    0.43
    瞰
    0.43
     sahab
    0.42
     ủy
    0.42
    Activations Density 0.001%

    No Known Activations