© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91529
    Prev
    Next
    INDEX
    Explanations

    explaining exceptions and conditions

    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
    s
    0.57
    re
    0.55
     presumably
    0.51
    h
    0.48
    Ể
    0.47
    ↵
    0.47
    #!/
    0.46
    t
    0.46
    presumably
    0.45
     inscriptions
    0.43
    POSITIVE LOGITS
     போராட்ட
    0.49
     분포
    0.48
    нил
    0.46
    }(\
    0.43
     කරන්න
    0.42
     সম্ভাব
    0.42
     iniziale
    0.42
     bbox
    0.41
     결정
    0.41
    ಿಸಿ
    0.40
    Activations Density 0.010%

    No Known Activations