© 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-262K
    7. 25952
    Prev
    Next
    INDEX
    Explanations

    show, try, want, interface, Redbubble

    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_262k_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
    
    0.48
    ٤
    0.45
    図書館
    0.44
    Mill
    0.44
    BinBuf
    0.42
     forbidding
    0.42
     پدر
    0.42
     obeys
    0.41
    antiates
    0.41
    InterfaceLine
    0.41
    POSITIVE LOGITS
     '*')
    0.45
     Jac
    0.40
     '*'
    0.40
     asterisk
    0.39
     "*"
    0.39
    ారో
    0.38
     perímetro
    0.38
     drawstring
    0.37
     Triton
    0.37
    quasar
    0.37
    Activations Density 0.000%

    No Known Activations