© 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. 181789
    Prev
    Next
    INDEX
    Explanations

    Tasting Collection British Columbia

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

    objects, AI, calculations, humans, prediction

    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
     “.
    0.55
    “.
    0.53
    〟
    0.48
    役に
    0.47
    “-
    0.46
    )”.
    0.45
    มน
    0.44
    ?”.
    0.44
    “…
    0.44
    ”…
    0.43
    POSITIVE LOGITS
     erster
    0.53
     שט
    0.48
    బ్
    0.47
     eruptions
    0.47
     adsor
    0.47
     Exams
    0.47
     الكسور
    0.46
    ismillah
    0.46
     abl
    0.46
     siendo
    0.46
    Activations Density 0.001%

    No Known Activations