© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11512
    Prev
    Next
    INDEX
    Explanations

    reaction between or of

    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_9_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
    ۰
    1.33
    ۵
    1.31
    Inject
    1.31
    ড
    1.28
    म
    1.28
    ۲
    1.25
    ম
    1.24
    ྰ
    1.24
     рынка
    1.22
    ᓲ
    1.22
    POSITIVE LOGITS
    ss
    1.36
    rang
    1.17
    gın
    1.16
    st
    1.14
    dan
    1.14
    at
    1.11
     jaws
    1.08
    ေါ
    1.07
    lah
    1.06
    dent
    1.04
    Activations Density 0.000%

    No Known Activations