© 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. 47787
    Prev
    Next
    INDEX
    Explanations

    Retribution, Mars, oven, library, damages, then, officials, leisure

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

    potentially complex or bordering

    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
    是从
    0.53
    PHONE
    0.47
    這是
    0.47
    是一个
    0.46
    这是
    0.46
     одино
    0.45
    м
    0.45
    Phone
    0.44
    বাব
    0.43
    是
    0.43
    POSITIVE LOGITS
    entlichen
    0.53
    entlich
    0.52
     tempHeader
    0.50
     मेघा
    0.48
     berichtet
    0.47
     homologs
    0.46
     resa
    0.46
    敉
    0.45
    ahlt
    0.45
    kennt
    0.44
    Activations Density 0.000%

    No Known Activations