© 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. 61039
    Prev
    Next
    INDEX
    Explanations

    preparing candidates

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

    predict future events or behaviors

    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
     disillusioned
    0.49
     obstructed
    0.49
     hindered
    0.46
     aftermarket
    0.46
     cramped
    0.46
     hampered
    0.45
     새로운
    0.44
    슌
    0.44
    승
    0.43
     disturbed
    0.43
    POSITIVE LOGITS
    pt
    0.44
     Auditor
    0.43
     तारे
    0.42
     obras
    0.42
    👤
    0.42
    🎷
    0.42
    🏺
    0.42
     auditor
    0.41
    說
    0.41
    🗯
    0.41
    Activations Density 0.000%

    No Known Activations