© 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. 161535
    Prev
    Next
    INDEX
    Explanations

    NTFS, OPP, go

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

    languages and geographical locations

    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
    evening
    0.40
     evening
    0.40
     understandable
    0.40
    美丽
    0.39
    这也
    0.39
    熊
    0.39
    旌
    0.39
     också
    0.38
     различ
    0.38
     것도
    0.38
    POSITIVE LOGITS
     Haven
    0.45
     hafa
    0.44
     उन्होंने
    0.42
    ownika
    0.40
    ²/
    0.38
    Kin
    0.38
     каза
    0.38
    akers
    0.37
     শনিবার
    0.37
    ğin
    0.37
    Activations Density 0.077%

    No Known Activations