© 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. 61468
    Prev
    Next
    INDEX
    Explanations

    combination ofreasonable attorneysDigital ofthree counts

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

    between those of

    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
    spannung
    0.45
    äten
    0.43
    enamefont
    0.43
     условиях
    0.42
     непосред
    0.41
     מר
    0.41
    :",
    0.40
    ceding
    0.39
     దూర
    0.39
    naf
    0.38
    POSITIVE LOGITS
    ঘু
    0.51
    让我
    0.48
     quello
    0.47
    Yours
    0.46
     Congreso
    0.45
     ditambah
    0.44
    ﺛ
    0.44
    िक्की
    0.42
     stone
    0.42
     yours
    0.42
    Activations Density 0.000%

    No Known Activations