© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 12161
    Prev
    Next
    INDEX
    Explanations

    instructions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    ו
    0.70
    וה
    0.68
    Be
    0.66
    e
    0.65
     Be
    0.65
    記得
    0.64
    おそらく
    0.64
    poss
    0.64
    故意
    0.63
    هو
    0.63
    POSITIVE LOGITS
     도입
    0.93
     নির
    0.82
     꼭
    0.82
     যৌগ
    0.82
    膂
    0.80
    ນາ
    0.79
     toNumber
    0.79
     Länder
    0.79
    katana
    0.79
     đua
    0.79
    Activations Density 0.000%

    No Known Activations