© 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-16K
    7. 2051
    Prev
    Next
    INDEX
    Explanations

    bash commands

    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_16k_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
    rends
    1.92
    y
    1.92
    am
    1.86
    rug
    1.85
    tive
    1.82
    ec
    1.80
    singular
    1.78
    t
    1.73
    材
    1.73
    days
    1.72
    POSITIVE LOGITS
     nucleation
    2.08
    䧉
    2.02
    ה
    2.00
     mái
    1.97
    洊
    1.96
     Repairs
    1.93
    ListNode
    1.89
     smacked
    1.88
     dearest
    1.88
    ها
    1.85
    Activations Density 0.227%

    No Known Activations