© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 58362
    Prev
    Next
    INDEX
    Explanations

    preposition following certain words

    np_acts-logits-general · gemini-2.5-flash-lite

    absorb, circuit, common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    稦
    0.49
    इजेशन
    0.48
     sulfate
    0.46
     аутох
    0.46
     یخ
    0.45
     desempenho
    0.45
     Slope
    0.45
     paleo
    0.44
     calomel
    0.44
    THING
    0.43
    POSITIVE LOGITS
    t
    0.49
    mond
    0.48
    md
    0.45
    d
    0.45
    mont
    0.44
    mem
    0.44
    bra
    0.41
    pr
    0.40
    uc
    0.40
    本日
    0.40
    Activations Density 0.000%

    No Known Activations