© 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. 175042
    Prev
    Next
    INDEX
    Explanations

    flown by helicopter

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

    astral, classification, audit, beaver, search

    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
     phản
    0.48
    Directive
    0.46
     אפ
    0.46
    WebApi
    0.46
    ৬
    0.44
    ²
    0.44
    🤠
    0.43
    :-
    0.43
    IEE
    0.43
     EventArgs
    0.43
    POSITIVE LOGITS
     tubular
    0.49
     terminado
    0.48
    逻辑
    0.47
     собира
    0.47
    ᱭ
    0.46
     spermat
    0.46
     отметил
    0.46
     பணியாற்ற
    0.46
    yemek
    0.45
     Со
    0.45
    Activations Density 0.001%

    No Known Activations