© 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. 41614
    Prev
    Next
    INDEX
    Explanations

    sweetened coconut

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

    prompts and placeholders

    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
    口味
    0.43
    ля
    0.43
    签
    0.42
    导师
    0.42
    오
    0.42
    밥
    0.42
    ごはん
    0.41
    食
    0.41
    福
    0.41
    一个
    0.41
    POSITIVE LOGITS
     bekannte
    0.57
    wijl
    0.52
     zowel
    0.51
     அடுத்து
    0.51
     erfüll
    0.50
     nécessairement
    0.50
     einzige
    0.50
     erne
    0.50
     ersche
    0.49
     pokrač
    0.49
    Activations Density 0.000%

    No Known Activations