© 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. 90048
    Prev
    Next
    INDEX
    Explanations

    house on US gun longing compose acupuncture discriminatory

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

    reliance after held

    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
    dì
    0.49
    зион
    0.44
    ルダー
    0.44
    韧
    0.43
     концу
    0.42
    程式
    0.41
    لې
    0.41
     współprac
    0.41
    ூ
    0.41
     límite
    0.41
    POSITIVE LOGITS
     Athletes
    0.45
     too
    0.44
     Referee
    0.44
    ycled
    0.44
    áč
    0.42
    ikker
    0.42
     TOO
    0.42
     Structures
    0.40
    achlor
    0.40
    瀆
    0.40
    Activations Density 0.002%

    No Known Activations