© 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. 12159
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming

    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
    로
    0.96
    0.95
    に
    0.90
    :
    0.88
    a
    0.85
    en
    0.82
    ต์
    0.80
    <h4>
    0.79
    hood
    0.78
     wi
    0.77
    POSITIVE LOGITS
    ൨
    1.15
    Ꭾ
    1.14
    FindingsResponse
    1.13
     INCIDENTAL
    1.12
    Ꮫ
    1.12
    ethylsulfanyl
    1.08
    subprocess
    1.06
     выполнения
    1.06
    returnValues
    1.05
    arrerol
    1.05
    Activations Density 0.154%

    No Known Activations