© 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. 161196
    Prev
    Next
    INDEX
    Explanations

    departments, parts, information, ceremonies

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

    place names and scientific terms

    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
    邵
    0.48
    ơi
    0.47
    sini
    0.45
    я
    0.45
     વૃ
    0.44
    сия
    0.44
    霏
    0.44
    lü
    0.43
    pools
    0.43
     pools
    0.43
    POSITIVE LOGITS
     microbe
    0.47
    _=
    0.46
     clade
    0.46
     Vancouver
    0.46
     Muscat
    0.46
    Manchester
    0.46
     caster
    0.45
     metaphor
    0.45
    TOTAL
    0.44
     Hadamard
    0.44
    Activations Density 0.000%

    No Known Activations