© 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. 4604
    Prev
    Next
    INDEX
    Explanations

    light and photography

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

    Check, errors, grabbing

    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
     અન્ય
    0.33
     podemos
    0.30
    ಯೇ
    0.30
    我也
    0.30
     motivates
    0.29
    而
    0.29
    或是
    0.29
    其它
    0.29
    ﻪ
    0.29
    一方で
    0.28
    POSITIVE LOGITS
     forbade
    0.34
     მათ
    0.30
    据说
    0.29
     gelungen
    0.29
     arresting
    0.29
     त्यांच्या
    0.28
     बराम
    0.28
     hesitated
    0.28
     ദിവസം
    0.28
     задержа
    0.28
    Activations Density 0.000%

    No Known Activations