© 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. 7539
    Prev
    Next
    INDEX
    Explanations

    linguistic structures and code elements

    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
    OPTV
    0.45
    τ
    0.41
    Really
    0.40
    ాగ
    0.39
     profitability
    0.38
    Hilbert
    0.38
    Sources
    0.38
    涘
    0.38
     transcendence
    0.38
     nonlinearity
    0.37
    POSITIVE LOGITS
    িয়ে
    0.46
     directly
    0.45
    tono
    0.45
    直接
    0.45
     proprietary
    0.44
     vattati
    0.43
     अनियमित
    0.43
     doğrudan
    0.43
     recognisable
    0.43
    ኾ
    0.43
    Activations Density 0.004%

    No Known Activations