© 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. 251157
    Prev
    Next
    INDEX
    Explanations

    utilities, phone, units, available

    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
    on
    0.66
    et
    0.59
    as
    0.58
    verw
    0.55
    it
    0.54
    w
    0.50
    ie
    0.48
    waarden
    0.48
    gegen
    0.48
    ë
    0.48
    POSITIVE LOGITS
    ޏ
    0.51
    رم
    0.50
    অভ
    0.48
    뜸
    0.48
    ନା
    0.47
    乚
    0.47
     ሞ
    0.46
    Ⴀ
    0.45
     বোঝ
    0.44
    inoceros
    0.44
    Activations Density 0.000%

    No Known Activations