© 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. 58219
    Prev
    Next
    INDEX
    Explanations

    or

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

    listing options or examples

    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
     officinalis
    0.46
    ף
    0.44
     alimentaire
    0.42
     flammable
    0.42
     puriso
    0.41
     pess
    0.40
     combustibles
    0.39
    酒店
    0.39
     preh
    0.38
    _
    0.38
    POSITIVE LOGITS
    หรือ
    0.65
     কিংবা
    0.59
     등으로
    0.59
     veya
    0.59
     혹은
    0.57
     või
    0.57
    或
    0.56
     অথবা
    0.56
     или
    0.55
     또는
    0.55
    Activations Density 0.004%

    No Known Activations