© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 40461
    Prev
    Next
    INDEX
    Explanations

    between words that are part of code or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    al
    0.51
    alena
    0.43
    িলিয়া
    0.43
    or
    0.40
    реза
    0.40
    alions
    0.40
    рина
    0.39
    颶
    0.39
    Koch
    0.38
     irmã
    0.38
    POSITIVE LOGITS
     Pakistani
    0.51
    ';
    0.50
    dbi
    0.49
    udev
    0.47
     Riders
    0.46
     d
    0.45
     डाउट्स
    0.45
    回目の
    0.45
     Rs
    0.45
     Kashmiri
    0.45
    Activations Density 0.015%

    No Known Activations