© 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. 225122
    Prev
    Next
    INDEX
    Explanations

    last week tonight

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

    operational capabilities

    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
    ع
    0.49
    :
    0.45
     Gartner
    0.45
    ٪
    0.40
    بح
    0.40
     Brookfield
    0.40
     Provided
    0.39
     CUT
    0.39
     Puente
    0.39
    ︰
    0.39
    POSITIVE LOGITS
     mania
    0.51
     مسئلے
    0.48
     родствен
    0.47
    trump
    0.47
    னால்
    0.46
    proble
    0.46
    ulosa
    0.46
    reactions
    0.46
    carrot
    0.45
     শ্রেণির
    0.44
    Activations Density 0.001%

    No Known Activations