© 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. 199680
    Prev
    Next
    INDEX
    Explanations

    instructional materials providing

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

    foundations, memory, theoretical, flexibility

    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
     stationed
    0.49
     ϕ
    0.46
     hosted
    0.46
     some
    0.45
     Some
    0.45
     SOME
    0.45
     december
    0.45
     startups
    0.45
     Zumba
    0.45
     Ao
    0.44
    POSITIVE LOGITS
    는
    0.50
     삽니다
    0.48
    입니다
    0.46
    갱
    0.46
    (":
    0.44
    왜
    0.44
    መሪያ
    0.43
     détails
    0.43
    Doctrine
    0.43
    됩니다
    0.43
    Activations Density 0.000%

    No Known Activations