© 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. 26745
    Prev
    Next
    INDEX
    Explanations

    expected pay

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

    Create, Results, making, joke, assert

    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
    ل
    0.55
    氣
    0.51
    ت
    0.48
    azone
    0.46
    भरा
    0.45
    ಇ
    0.45
    لن
    0.45
    ఇ
    0.45
    贅
    0.44
    鎸
    0.44
    POSITIVE LOGITS
    :
    0.56
     Future
    0.55
     Gli
    0.54
     Consiglio
    0.53
     Carb
    0.52
     Tolerance
    0.52
     Comité
    0.51
     Comisión
    0.51
     Dublin
    0.51
     Ayam
    0.51
    Activations Density 0.000%

    No Known Activations