© 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. 223376
    Prev
    Next
    INDEX
    Explanations

    scss styling language

    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
     &_
    0.43
    >\<^
    0.41
     &__
    0.41
     drawed
    0.40
     Kochubei
    0.40
     subalgebra
    0.39
    ']:
    0.38
     olympi
    0.38
    ሁ
    0.38
     suppuration
    0.38
    POSITIVE LOGITS
    ano
    0.42
    ira
    0.41
    itando
    0.40
    med
    0.39
    adic
    0.38
    a
    0.37
    web
    0.37
    altra
    0.36
    dea
    0.36
    ("#
    0.36
    Activations Density 0.001%

    No Known Activations