© 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. 126988
    Prev
    Next
    INDEX
    Explanations

    citing the, poking out, looking for

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

    offers happening

    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
     గణ
    0.45
     มาก
    0.44
     dehuman
    0.41
     ഇഷ്ട
    0.41
    வற்ற
    0.40
     먼저
    0.40
     LESS
    0.40
    ](./
    0.40
     हटाएं
    0.39
     rearrangement
    0.39
    POSITIVE LOGITS
    contours
    0.44
    ্লার
    0.44
    یدن
    0.43
     σου
    0.43
     μία
    0.42
     Toxicology
    0.41
    2
    0.41
    ския
    0.40
     терапии
    0.40
     étamines
    0.40
    Activations Density 0.002%

    No Known Activations