© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 40532
    Prev
    Next
    INDEX
    Explanations

    grape and grape varieties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ap
    1.91
    r
    1.77
    ay
    1.73
    id
    1.58
    ad
    1.55
    ut
    1.45
    am
    1.42
    it
    1.32
    OT
    1.31
    an
    1.30
    POSITIVE LOGITS
    ต์
    1.58
    IONAL
    1.55
     solstice
    1.45
    幔
    1.43
     grapes
    1.40
     epistle
    1.39
    စိတ်အပိုင်း
    1.39
     raffin
    1.38
     talisman
    1.38
     Está
    1.37
    Activations Density 0.007%

    No Known Activations