© 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. 242980
    Prev
    Next
    INDEX
    Explanations

    since I have

    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
    今日の
    0.51
    本日
    0.44
     이날
    0.44
     моих
    0.44
     구분
    0.44
    今日は
    0.44
    粆
    0.43
    优点
    0.42
    昨日
    0.41
     MAIN
    0.40
    POSITIVE LOGITS
     disastrous
    0.47
     pandemics
    0.43
    eny
    0.42
    negl
    0.41
    Pres
    0.41
     अचानक
    0.41
     pandemic
    0.40
    pandemic
    0.40
    ,\,
    0.40
     Negeri
    0.39
    Activations Density 0.082%

    No Known Activations