© 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. 21220
    Prev
    Next
    INDEX
    Explanations

    cleaning easy, cleanup simple, design should

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

    things become unreliable or biased

    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
     म्हणून
    0.46
     Immunity
    0.46
     대상으로
    0.45
    immunity
    0.45
     பயன்படுத்தி
    0.45
     Lö
    0.44
     Wunsch
    0.44
    t
    0.44
    immune
    0.44
    为人
    0.44
    POSITIVE LOGITS
    姗
    0.46
    چھے
    0.42
     />}/>
    0.42
    ahanam
    0.42
    ες
    0.40
    льний
    0.40
    ρού
    0.40
    OS
    0.39
    اہے
    0.39
    mPreview
    0.39
    Activations Density 0.000%

    No Known Activations