© 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. 32947
    Prev
    Next
    INDEX
    Explanations

    Next article links

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

    mechanism, original, reduced

    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
    स्‍त
    0.52
    igham
    0.48
    काने
    0.47
    afstand
    0.47
    atthena
    0.46
     juni
    0.46
    gameField
    0.44
    诓
    0.44
     persegi
    0.44
     изме
    0.43
    POSITIVE LOGITS
     ESG
    0.48
    SNS
    0.45
    軽量
    0.45
    な
    0.44
    インスト
    0.44
     Jpn
    0.43
    ビジネス
    0.42
    ESG
    0.42
     Seiko
    0.41
    کم
    0.41
    Activations Density 0.000%

    No Known Activations