© 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. 217307
    Prev
    Next
    INDEX
    Explanations

    banking begins

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

    access to specific details

    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
    qk
    0.45
    führer
    0.44
    \">
    0.43
     Shun
    0.43
     cứu
    0.43
     লুকিয়ে
    0.42
    '></
    0.42
    츈
    0.42
     Ignatius
    0.41
     হয়েছিলো
    0.41
    POSITIVE LOGITS
    ழை
    0.45
    sprogram
    0.42
     तेरे
    0.40
    ուս
    0.40
    omatik
    0.39
    performs
    0.39
    मौसम
    0.39
     ɖ
    0.38
     мор
    0.38
    予測
    0.38
    Activations Density 0.000%

    No Known Activations