© 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. 28608
    Prev
    Next
    INDEX
    Explanations

    app features

    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
     Announcements
    0.52
    Ў
    0.50
     thoſe
    0.46
    对称
    0.45
    When
    0.44
    𒀝
    0.44
    Those
    0.43
    Were
    0.43
    Caracter
    0.43
    诏
    0.43
    POSITIVE LOGITS
     mineral
    0.48
     plus
    0.48
    ac
    0.46
    ut
    0.46
    k
    0.45
     management
    0.45
    plus
    0.44
     prevention
    0.43
     resort
    0.43
     forestry
    0.42
    Activations Density 0.006%

    No Known Activations