© 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. 47356
    Prev
    Next
    INDEX
    Explanations

    down themessages like" Wideringyou musttimefibrin coveringthree golden

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

    integer data types

    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
    palindrome
    0.46
    ccncc
    0.45
    CCCO
    0.45
    EXECUT
    0.45
    넬
    0.45
     contemporary
    0.44
     হো
    0.44
    unches
    0.44
    н
    0.44
    Palmer
    0.43
    POSITIVE LOGITS
     océano
    0.48
    ానని
    0.46
     elke
    0.44
     mètre
    0.44
    ľov
    0.44
     perfekte
    0.43
     améliorer
    0.43
     takže
    0.42
     mier
    0.42
     सगळ्या
    0.42
    Activations Density 0.000%

    No Known Activations