© 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. 11892
    Prev
    Next
    INDEX
    Explanations

    spice and spice blends

    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
    sächlich
    2.85
    dür
    2.58
    isEqualTo
    2.43
    적으로
    2.43
    у
    2.43
     mimetype
    2.36
     sikap
    2.35
     predictable
    2.30
     applicable
    2.29
    ாக
    2.25
    POSITIVE LOGITS
    e
    3.01
    ee
    2.46
    oo
    2.30
    eers
    2.28
    eaa
    2.28
    न
    2.26
    ﺘ
    2.24
    р
    2.21
    ્
    2.19
    От
    2.18
    Activations Density 0.007%

    No Known Activations