© 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. 73580
    Prev
    Next
    INDEX
    Explanations

    constitute, annual membership, grow hemp

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

    categories and slogans

    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
    NING
    0.50
    course
    0.45
     slopes
    0.45
     오전
    0.44
    androidx
    0.43
     gains
    0.42
    ｰ
    0.42
     sheets
    0.42
     aqueous
    0.42
     course
    0.41
    POSITIVE LOGITS
     चिल्ड्रन
    0.46
     revista
    0.42
     produtt
    0.42
     évaluation
    0.42
    regul
    0.42
     উপস্থাপন
    0.42
    抨
    0.41
     potřeb
    0.40
     אות
    0.40
     புற
    0.40
    Activations Density 0.000%

    No Known Activations