© 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. 206585
    Prev
    Next
    INDEX
    Explanations

    villa, caption, squirrels, boks, thought, wildlife, respectable

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

    undercover cop, Microsoft uses

    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
     complicating
    0.54
    lo
    0.50
     druge
    0.47
    n
    0.47
     andere
    0.46
    elden
    0.46
    frost
    0.45
    les
    0.45
    son
    0.44
    axy
    0.44
    POSITIVE LOGITS
    を選択
    0.46
    گز
    0.46
     MDC
    0.45
    َّة
    0.45
    <unused51>
    0.45
    َرَ
    0.45
    σίας
    0.44
    اري
    0.44
    ρίας
    0.44
    ತರ
    0.43
    Activations Density 0.000%

    No Known Activations