© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 13196
    Prev
    Next
    INDEX
    Explanations

    semi and half

    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
    寇
    1.06
     nazw
    1.04
    리아
    0.97
     marqués
    0.96
     einiger
    0.95
    ウド
    0.95
    larının
    0.94
     žád
    0.94
    事項
    0.93
    र्में
    0.93
    POSITIVE LOGITS
     dozen
    1.63
    dozen
    1.35
    导体
    1.34
    胱
    1.25
     दर्जन
    1.18
    iotic
    1.11
    moon
    1.11
     vời
    1.08
    heartedly
    1.08
    breeds
    1.01
    Activations Density 0.041%

    No Known Activations