© 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. 40-GEMMASCOPE-2-RES-262K
    7. 210437
    Prev
    Next
    INDEX
    Explanations

    button bootstrap classes

    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_40_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
    мини
    0.45
     labor
    0.41
     mini
    0.41
    懵
    0.40
     BitmapFactory
    0.38
     ev
    0.37
    шению
    0.37
    mini
    0.37
     Ruman
    0.37
     min
    0.36
    POSITIVE LOGITS
    »),
    0.45
    ധ്യ
    0.44
    DARK
    0.43
    ),[
    0.41
    goTo
    0.40
    😺
    0.40
    感
    0.39
    煦
    0.39
     製
    0.39
    millan
    0.38
    Activations Density 0.003%

    No Known Activations