© 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. 155198
    Prev
    Next
    INDEX
    Explanations

    names and abbreviations

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

    words starting with a

    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
    SystemColors
    0.44
     รา
    0.40
    ၆
    0.39
    ColorBit
    0.38
    ≲
    0.38
    ܵ
    0.37
     dieting
    0.37
     merveille
    0.37
     rendszer
    0.37
    રા
    0.37
    POSITIVE LOGITS
     AVR
    0.45
     A
    0.45
     UA
    0.44
     ANI
    0.43
     AGN
    0.42
    螈
    0.42
     AN
    0.41
     Increased
    0.41
     ACS
    0.41
     ASH
    0.41
    Activations Density 0.199%

    No Known Activations