© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202707
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     malignancies
    0.54
     polysaccharides
    0.51
     moieties
    0.50
     모양
    0.47
     స్ప
    0.46
    焓
    0.46
     scalars
    0.45
     allele
    0.45
     ambiguities
    0.45
     radiates
    0.45
    POSITIVE LOGITS
    zo
    0.53
    หาคม
    0.46
    ותר
    0.46
     свої
    0.45
    awt
    0.44
    ו
    0.44
    Bron
    0.42
    es
    0.42
    ื้อง
    0.41
    цаў
    0.41
    Activations Density 0.000%

    No Known Activations