© 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. 202707
    Prev
    Next
    INDEX
    Explanations

    numbers and section

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

    compliance and risk

    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
     malignancies
    0.60
     polysaccharides
    0.51
     ambiguities
    0.49
     moieties
    0.48
     radiates
    0.48
     స్ప
    0.46
    焓
    0.46
     모양
    0.46
     이차
    0.46
     allele
    0.45
    POSITIVE LOGITS
     свої
    0.51
    zo
    0.49
    หาคม
    0.49
    ותר
    0.46
    ו
    0.46
    цаў
    0.44
    くちゃ
    0.43
    combe
    0.43
    ्रम
    0.42
    ื้อง
    0.42
    Activations Density 0.000%

    No Known Activations