Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 1405
    Prev
    Next
    INDEX
    Explanations

    0 followed by 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    CR
    1.60
     CR
    1.57
    Cr
    1.46
    cr
    1.44
    RC
    1.41
    C
    1.41
    Rc
    1.40
     Cr
    1.38
    rc
    1.38
    CRE
    1.35
    POSITIVE LOGITS
     Shetland
    0.75
     Pantone
    0.71
     Wizards
    0.67
     avenida
    0.64
     talleres
    0.62
     Pony
    0.61
    襄
    0.61
    häng
    0.60
     Floyd
    0.60
     Yoshi
    0.60
    Activations Density 1.956%

    No Known Activations