© 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. 98240
    Prev
    Next
    INDEX
    Explanations

    displayGamesrollergardenhelping

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

    Warframe and mixers

    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
    地に
    0.49
     toliko
    0.49
    吡
    0.48
    ꯣ
    0.47
    ず
    0.46
     prije
    0.45
    ложить
    0.45
    மான்
    0.45
    纂
    0.45
    வான்
    0.45
    POSITIVE LOGITS
     照片
    0.48
    oint
    0.45
    revolutionary
    0.43
    estado
    0.43
     Technologies
    0.43
    having
    0.42
     ভালোবাসা
    0.42
     splashing
    0.41
     abon
    0.41
    磚
    0.41
    Activations Density 0.001%

    No Known Activations