© 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. 190296
    Prev
    Next
    INDEX
    Explanations

    labeled as

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

    specific language or names

    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
    apayati
    0.53
     produ
    0.51
    ਤੇ
    0.47
     ಶಿವ
    0.46
    ニ
    0.46
    ಶಿ
    0.45
     פּ
    0.44
    ائیں۔
    0.44
     investi
    0.43
     benef
    0.43
    POSITIVE LOGITS
    гідно
    0.47
     freaking
    0.46
     গলায়
    0.45
     Riggs
    0.45
    魂
    0.45
     COMMUNICATIONS
    0.43
     Cros
    0.43
     вроде
    0.43
    мм
    0.42
    ك
    0.42
    Activations Density 0.000%

    No Known Activations