© 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. 158747
    Prev
    Next
    INDEX
    Explanations

    reset your password or shaver

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

    distance further

    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
     pkg
    0.44
     flashes
    0.42
    ุณ
    0.42
    끽
    0.41
     vyu
    0.41
     revolved
    0.41
    pkg
    0.40
     wrapped
    0.39
     particulares
    0.39
    癤
    0.39
    POSITIVE LOGITS
     Städte
    0.47
     Başkanı
    0.46
     Jaaye
    0.46
    getResult
    0.45
    inity
    0.45
    atás
    0.45
    playSound
    0.45
    anı
    0.44
     Govern
    0.44
     Kendrick
    0.43
    Activations Density 0.000%

    No Known Activations