© 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. 209315
    Prev
    Next
    INDEX
    Explanations

    condition, compatibility, renovations

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

    foreign characters and code

    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
     MEET
    0.54
     మ్యాచ్
    0.53
     格
    0.52
     നേതാ
    0.49
     బోర్
    0.49
     নিজেই
    0.48
     አገልግሎ
    0.47
     リア
    0.47
     沒有
    0.47
     applauded
    0.46
    POSITIVE LOGITS
    You
    0.52
     you
    0.49
    1
    0.46
    নীয়
    0.46
     confisc
    0.45
    ん
    0.45
    ạt
    0.45
     másc
    0.45
    й
    0.45
     phosphates
    0.43
    Activations Density 0.000%

    No Known Activations