© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9736
    Prev
    Next
    INDEX
    Explanations

    some followed by noun

    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
    ा
    3.16
    써
    2.84
     vivido
    2.49
     celé
    2.42
    خدم
    2.38
    ことになる
    2.37
    أ
    2.33
    más
    2.33
     mêmes
    2.24
    ास
    2.22
    POSITIVE LOGITS
    ب
    4.64
    bodies
    3.02
    how
    2.74
     semblance
    2.73
    ones
    2.69
     extent
    2.60
    باس
    2.49
    place
    2.48
    值
    2.43
    pony
    2.34
    Activations Density 0.106%

    No Known Activations