© 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. 78741
    Prev
    Next
    INDEX
    Explanations

    boutique, third, thicknesses, sets

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

    places

    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
     Що
    0.45
    Tiene
    0.41
     kdo
    0.39
     ethic
    0.38
    蠣
    0.38
    ClrType
    0.38
     tender
    0.38
    Ted
    0.37
     hatte
    0.37
     dnes
    0.37
    POSITIVE LOGITS
    空中
    0.45
     जाईल
    0.42
     பாதை
    0.42
    ◠
    0.42
     गार्ड
    0.42
    開啟
    0.42
    களில்
    0.41
    stethoscope
    0.40
    ='./
    0.40
     ショルダーバッグ
    0.39
    Activations Density 0.000%

    No Known Activations