© 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. 105381
    Prev
    Next
    INDEX
    Explanations

    ECHO HIV volunteer job

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

    understanding when where systems count

    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
    ویان
    0.47
     دیگری
    0.47
    ާއ
    0.45
    ನ್ನೂ
    0.44
     آدم
    0.44
    ناو
    0.44
    킵
    0.41
     dragging
    0.40
    게요
    0.40
    goTo
    0.40
    POSITIVE LOGITS
     shopper
    0.52
     över
    0.50
     Cities
    0.47
    1
    0.46
    ɡ
    0.46
    ’)
    0.46
    omé
    0.46
    <0xCD>
    0.45
    RB
    0.45
    árd
    0.45
    Activations Density 0.000%

    No Known Activations