© 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. 161782
    Prev
    Next
    INDEX
    Explanations

    take advantage

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

    you could, you can, here for

    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
    িলিয়া
    0.45
    வினை
    0.45
    ങ്ങനെ
    0.44
    étais
    0.43
    ㄧ
    0.43
     احساس
    0.41
     privilegi
    0.41
     enlight
    0.40
     fachada
    0.40
    porcion
    0.40
    POSITIVE LOGITS
    S
    0.49
    N
    0.47
     να
    0.46
     και
    0.44
    🩺
    0.43
     và
    0.43
    V
    0.42
     πολλ
    0.42
     \
    0.42
    یاں
    0.42
    Activations Density 0.001%

    No Known Activations