© 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. 100808
    Prev
    Next
    INDEX
    Explanations

    place and context

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

    damage and soreness

    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
     Officials
    0.50
    밂
    0.49
    顺利
    0.48
    Officials
    0.48
    ഹമ്മ
    0.48
     Brochure
    0.47
     REFER
    0.46
     CANADA
    0.45
    ఓ
    0.45
    ोजक
    0.45
    POSITIVE LOGITS
    destroyed
    0.55
     destroyed
    0.53
    consumed
    0.52
    exported
    0.51
     plunder
    0.51
    human
    0.49
     human
    0.48
     archae
    0.48
     chronically
    0.47
    ancient
    0.47
    Activations Density 0.000%

    No Known Activations