© 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. 8485
    Prev
    Next
    INDEX
    Explanations

    it is essential

    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
    ᠣ
    0.70
     hone
    0.67
    bef
    0.67
    bill
    0.64
    ari
    0.63
    EXP
    0.63
    vol
    0.62
    ADV
    0.62
    cyl
    0.62
    QL
    0.62
    POSITIVE LOGITS
     Необходимо
    0.93
     超
    0.91
     iniciando
    0.91
     Й
    0.88
     jälkeen
    0.87
     jedną
    0.87
     źród
    0.87
     以上
    0.87
     необхідно
    0.87
     要求
    0.86
    Activations Density 0.008%

    No Known Activations