© 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. 42073
    Prev
    Next
    INDEX
    Explanations

    descriptive concepts and phrases

    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
     pogled
    0.50
    ത്തിലേക്ക്
    0.49
     හෝ
    0.49
    Ꭷ
    0.48
    streetlight
    0.48
    낯
    0.48
    کروچ
    0.48
     olvid
    0.47
    ედერ
    0.47
    łuż
    0.47
    POSITIVE LOGITS
     Des
    0.44
    )
    0.44
    ↵
    0.43
     U
    0.43
     MV
    0.42
     Insurance
    0.42
     Minimum
    0.41
     Marine
    0.41
     Term
    0.41
     clocked
    0.40
    Activations Density 0.002%

    No Known Activations