© 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. 403
    Prev
    Next
    INDEX
    Explanations

    define statements

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

    LaTeX and Scheme code structure

    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
    नाश
    0.46
     vrouwen
    0.44
    NaOH
    0.41
     asesinato
    0.41
     vattum
    0.41
    🏟
    0.41
    OrderFlight
    0.40
    Callories
    0.40
    នុស្ស
    0.40
     perfección
    0.40
    POSITIVE LOGITS
     R
    0.53
     d
    0.47
     V
    0.46
     T
    0.46
     W
    0.45
     "
    0.44
    x
    0.44
     N
    0.43
     x
    0.43
     P
    0.42
    Activations Density 0.000%

    No Known Activations