© 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. 58438
    Prev
    Next
    INDEX
    Explanations

    lift up, you get, high euthanasia

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

    multilingual text identification

    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
    த
    0.46
    вели
    0.46
    веден
    0.46
    odne
    0.46
    ט
    0.45
     llam
    0.45
    YER
    0.45
    веде
    0.44
     Neces
    0.44
    ネルギー
    0.43
    POSITIVE LOGITS
    ैश
    0.42
     فاذا
    0.42
    Mash
    0.41
     diarr
    0.40
     দামে
    0.40
    ⒉
    0.40
    གྲ
    0.40
    ⅴ
    0.40
    Wall
    0.39
     régional
    0.39
    Activations Density 0.000%

    No Known Activations