© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 223
    Prev
    Next
    INDEX
    Explanations

    Datalog

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     more
    1.05
     not
    0.98
     더
    0.86
    rát
    0.84
     в
    0.80
    ,
    0.80
    τί
    0.79
     random
    0.79
    න
    0.78
     sper
    0.78
    POSITIVE LOGITS
     sighed
    1.07
    ScriptBuf
    1.02
     joseph
    1.00
     Burgundy
    1.00
    BlockUsed
    0.99
    lyPlugin
    0.97
     chiesa
    0.97
     tàu
    0.97
     excavations
    0.97
    TempBuffer
    0.96
    Activations Density 2.598%

    No Known Activations