© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 36823
    Prev
    Next
    INDEX
    Explanations

    following prepositions or connectors

    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
    сно
    1.47
    ோ
    1.46
    ING
    1.45
     underside
    1.45
     noodle
    1.44
    windigkeit
    1.38
    😎
    1.36
    ся
    1.35
    Lucida
    1.34
     disregarding
    1.34
    POSITIVE LOGITS
    mäßig
    2.19
    memorial
    2.11
    mäß
    2.08
    m
    2.08
    น
    2.06
    son
    2.00
    ed
    1.94
    ம்
    1.94
    morning
    1.91
    isation
    1.89
    Activations Density 0.000%

    No Known Activations