© 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. 3160
    Prev
    Next
    INDEX
    Explanations

    multiple

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

    multiple items

    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
     八
    0.71
     ۸
    0.63
     पाँच
    0.63
     moſt
    0.62
     सम्पूर्ण
    0.62
    quatre
    0.61
     jóvenes
    0.61
     九
    0.61
     ی
    0.61
    floxacin
    0.61
    POSITIVE LOGITS
     sclerosis
    1.26
     multiple
    1.02
     Multiple
    0.95
    Multiple
    0.84
     multi
    0.82
    multiple
    0.79
     myeloma
    0.78
    複数の
    0.76
    多个
    0.76
     Multi
    0.72
    Activations Density 0.040%

    No Known Activations