© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202340
    Prev
    Next
    INDEX
    Explanations

    prevents uncontrolled

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    瑆
    0.47
    安慰
    0.47
    ApiException
    0.46
    Elig
    0.46
    ADE
    0.45
    Disponible
    0.43
     angene
    0.43
     ກ
    0.43
    Jed
    0.43
    Proveedor
    0.43
    POSITIVE LOGITS
    ەل
    0.46
    at
    0.43
    ரை
    0.42
     Coating
    0.42
     gerais
    0.42
     mágico
    0.41
     blah
    0.41
     Happen
    0.40
     Pairing
    0.40
    onian
    0.40
    Activations Density 0.000%

    No Known Activations