© 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. 35122
    Prev
    Next
    INDEX
    Explanations

    cane / sugarcane

    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
    ية
    1.72
    setVerticalGroup
    1.39
    1.39
    gruppen
    1.38
    gruppe
    1.32
    灣
    1.32
    ções
    1.31
    u
    1.30
    }$,
    1.27
    ح
    1.26
    POSITIVE LOGITS
    ಯಲ್ಲಿ
    1.71
    th
    1.42
     voltar
    1.42
     काफ
    1.39
    たい
    1.34
    что
    1.34
    <0x8C>
    1.34
     davanti
    1.34
    Итак
    1.34
     avere
    1.33
    Activations Density 0.002%

    No Known Activations