© 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. 90875
    Prev
    Next
    INDEX
    Explanations

    describes actions or possibilities

    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
     ασ
    0.63
     ג
    0.49
    ش
    0.48
    մ
    0.48
    रह
    0.48
    𝔯
    0.47
     punctatis
    0.47
    डिज
    0.46
    मर
    0.46
     دقیق
    0.46
    POSITIVE LOGITS
     trajectory
    0.46
    (
    0.46
     ধরন
    0.44
    勧
    0.44
     equatorial
    0.42
     [\
    0.41
     finishers
    0.41
     timing
    0.40
     bishop
    0.39
     RARRAY
    0.39
    Activations Density 0.007%

    No Known Activations