© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5895
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    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
    going
    1.66
    toned
    1.59
    soaked
    1.51
    И
    1.50
    ness
    1.45
    >):
    1.44
    heastern
    1.40
     thúc
    1.37
     upbringing
    1.35
    transformed
    1.35
    POSITIVE LOGITS
    ان
    2.89
    на
    2.50
    न
    2.48
    en
    2.39
    oy
    2.39
    enin
    2.28
    ో
    2.27
    u
    2.25
    ן
    2.25
    ا
    2.20
    Activations Density 0.020%

    No Known Activations