© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13403
    Prev
    Next
    INDEX
    Explanations

    raising to a power

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

    power of

    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
    दून
    0.46
    కార
    0.44
    谲
    0.43
    GoString
    0.41
     তোমার
    0.41
    Geplaatst
    0.41
    োপাধ্যায়
    0.41
     منك
    0.40
     كرة
    0.40
     کاکروچ
    0.40
    POSITIVE LOGITS
     –
    0.48
     -->
    0.42
     −
    0.41
     minus
    0.41
     －
    0.40
    ２
    0.39
    ",
    0.38
    р
    0.38
    ться
    0.38
    2
    0.38
    Activations Density 0.000%

    No Known Activations