© 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-65K
    7. 7572
    Prev
    Next
    INDEX
    Explanations

    Let, Left, clicking links

    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_65k_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
    true
    0.77
    innings
    0.76
    STATIC
    0.74
    static
    0.72
    ground
    0.71
    unlock
    0.69
    ApiController
    0.67
    Ϫ
    0.65
    status
    0.65
    ener
    0.65
    POSITIVE LOGITS
     présentation
    0.91
     präsentiert
    0.88
     êtres
    0.82
    tesy
    0.81
     tret
    0.81
     ক্রয়
    0.79
     Presented
    0.79
     Charm
    0.78
     immagini
    0.77
     Dank
    0.75
    Activations Density 0.001%

    No Known Activations