© 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. 55291
    Prev
    Next
    INDEX
    Explanations

    do not let or pass through

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

    financial security, creativity, adventure

    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
     dissemination
    0.50
    대학교
    0.49
     disseminating
    0.48
     நடைபெ
    0.48
     moratorium
    0.48
    زب
    0.46
     nhật
    0.45
    ᙱ
    0.45
     benchmarks
    0.44
     benches
    0.44
    POSITIVE LOGITS
    మాట
    0.50
    Mit
    0.46
     gelungen
    0.44
    Wash
    0.43
    Funcion
    0.43
     ادب
    0.42
     Hfn
    0.41
     Luego
    0.40
    Riga
    0.40
     verfügen
    0.40
    Activations Density 0.000%

    No Known Activations