© 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. 13136
    Prev
    Next
    INDEX
    Explanations

    undefined concepts and queries

    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
     Selamat
    0.62
    睐
    0.62
    一步
    0.58
    チン
    0.57
     kontra
    0.57
     Brings
    0.57
    㺪
    0.57
    특히
    0.57
    డ
    0.57
    thern
    0.56
    POSITIVE LOGITS
     unknown
    3.08
    Unknown
    2.67
    unknown
    2.65
     unspecified
    2.63
     Unknown
    2.60
     unclear
    2.58
     undetermined
    2.55
     неизвест
    2.38
     unidentified
    2.38
     undefined
    2.27
    Activations Density 0.510%

    No Known Activations