© 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. 32422
    Prev
    Next
    INDEX
    Explanations

    legal indemnification clauses

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

    biometric sequence process

    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
    дай
    0.43
    ))&&(
    0.43
     considère
    0.42
     подрост
    0.42
     数字
    0.42
    方面的
    0.42
    㞖
    0.41
    ief
    0.41
     начина
    0.40
    这一点
    0.40
    POSITIVE LOGITS
     ourselves
    0.52
     lanes
    0.45
     uneasy
    0.45
     wavy
    0.44
     waves
    0.43
     greasy
    0.42
     réfrig
    0.41
     restless
    0.41
    ;%(
    0.41
    winds
    0.41
    Activations Density 0.000%

    No Known Activations