© 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. 68571
    Prev
    Next
    INDEX
    Explanations

    alternatives or, mitigate against

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

    understanding why

    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
     verpflicht
    0.53
    OT
    0.45
    CTION
    0.44
     Identify
    0.43
    夼
    0.43
     PDFs
    0.42
     ചരി
    0.42
     Growers
    0.42
     Allow
    0.41
     Loads
    0.41
    POSITIVE LOGITS
    <td>
    0.49
     stead
    0.45
    ớt
    0.45
    נן
    0.45
    0.44
    ắng
    0.44
    นาน
    0.44
    医药
    0.43
     benim
    0.42
    ấc
    0.42
    Activations Density 0.000%

    No Known Activations