© 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. 235831
    Prev
    Next
    INDEX
    Explanations

    legitimacy or bosses

    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
     Alej
    0.49
    arcía
    0.47
    g
    0.46
    of
    0.46
    antina
    0.45
    Syair
    0.45
    Matrix
    0.45
    stackrel
    0.45
     Woodruff
    0.45
    !
    0.44
    POSITIVE LOGITS
     innych
    0.51
     但
    0.47
     ولی
    0.47
     petits
    0.45
    ίνεται
    0.43
    としても
    0.43
     हद
    0.43
     bosses
    0.42
     legitimacy
    0.42
    ீரல்
    0.41
    Activations Density 0.000%

    No Known Activations