© 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. 20106
    Prev
    Next
    INDEX
    Explanations

    based on real-world observations

    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
     मोड़
    0.52
    वली
    0.50
    lső
    0.48
    avascript
    0.46
    𝒌
    0.46
     новый
    0.46
    igm
    0.45
    ".[
    0.45
    ight
    0.45
    uart
    0.45
    POSITIVE LOGITS
     prominence
    0.46
     judicious
    0.44
     efficacy
    0.43
     comparability
    0.43
    зяй
    0.42
     conspicuous
    0.42
     Brésil
    0.41
    йдз
    0.40
     enforcement
    0.40
     equities
    0.40
    Activations Density 0.001%

    No Known Activations