© 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-16K
    7. 12127
    Prev
    Next
    INDEX
    Explanations

    contact us

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

    contact us

    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_16k_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
     있
    0.42
     esperado
    0.41
    -;
    0.41
    珊
    0.41
    them
    0.40
    不好
    0.40
    远离
    0.40
    不多
    0.39
    くない
    0.39
    ่านั้น
    0.38
    POSITIVE LOGITS
    াড়
    0.52
    )=\
    0.45
    াড়
    0.44
    মূ
    0.44
     uitgen
    0.44
     dumped
    0.44
     summar
    0.43
     сайті
    0.42
    are
    0.42
     fetched
    0.42
    Activations Density 0.052%

    No Known Activations