© 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-65K
    7. 61571
    Prev
    Next
    INDEX
    Explanations

    character Dynamics AK solutions protection witnessed

    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_65k_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
    2
    0.67
    3
    0.66
    6
    0.64
    7
    0.56
    4
    0.55
    1
    0.53
    9
    0.53
    D
    0.49
    i
    0.47
    5
    0.47
    POSITIVE LOGITS
     celebrities
    0.52
     eighty
    0.50
     differentiator
    0.47
    ב
    0.47
     எட்டு
    0.47
     improb
    0.46
    มี
    0.46
     শ্রীযুক্ত
    0.46
     each
    0.45
     unicode
    0.45
    Activations Density 0.002%

    No Known Activations