© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43943
    Prev
    Next
    INDEX
    Explanations

    common word followed by common phrase

    np_acts-logits-general · gemini-2.5-flash-lite

    degrees, characteristics, medium rare, professor, rms, dust swirling, votes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ك
    0.52
    Мар
    0.41
    鍱
    0.41
    비
    0.40
     Elektrokh
    0.40
    焱
    0.38
    מס
    0.38
    кугӀ
    0.38
    شي
    0.38
    ని
    0.38
    POSITIVE LOGITS
    （
    0.58
    ↵↵
    0.55
     A
    0.55
     B
    0.50
    ，
    0.49
    ,
    0.48
     T
    0.47
     （
    0.46
    ation
    0.46
    -
    0.45
    Activations Density 0.130%

    No Known Activations