© 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. 219905
    Prev
    Next
    INDEX
    Explanations

    ordering refund

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

    physically moves or calculations

    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
    <0x80>
    0.53
    OK
    0.49
    сни
    0.48
    atas
    0.48
    F
    0.48
    O
    0.46
    لال
    0.46
    ներ
    0.46
    w
    0.45
    A
    0.45
    POSITIVE LOGITS
     Vlad
    0.48
     சரியான
    0.48
     eminently
    0.48
     فاصله
    0.48
     pomocy
    0.47
     যোগ্যতা
    0.47
     dukungan
    0.47
     translocation
    0.47
     slouch
    0.47
     Macron
    0.46
    Activations Density 0.001%

    No Known Activations