© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135535
    Prev
    Next
    INDEX
    Explanations

    item, inventory, series, name, naked, stack, classical

    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
     głównie
    0.48
     연구
    0.47
     nech
    0.47
     wzglę
    0.46
     книг
    0.46
     rzeczyw
    0.46
     년
    0.46
    Ꮡ
    0.46
     consacré
    0.45
    ทีม
    0.45
    POSITIVE LOGITS
    expand
    0.48
    maintenance
    0.45
    是否
    0.45
    seek
    0.42
    youth
    0.42
     ordinary
    0.42
    budget
    0.42
    derive
    0.42
    reversible
    0.42
    aware
    0.41
    Activations Density 0.002%

    No Known Activations