© 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. 97375
    Prev
    Next
    INDEX
    Explanations

    domain data

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

    whisper compressed period

    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
     多く
    0.58
     こう
    0.51
     개
    0.49
     MEM
    0.47
     শ্রেষ্ঠ
    0.47
     permutation
    0.46
    ก
    0.46
    多く
    0.46
    TH
    0.45
     종합
    0.45
    POSITIVE LOGITS
    minded
    0.47
    গের
    0.46
    Woods
    0.46
    hanahu
    0.45
    ப்பான்
    0.45
    వడం
    0.44
    gown
    0.44
    Mind
    0.44
    habitat
    0.43
    Taj
    0.43
    Activations Density 0.000%

    No Known Activations