© 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. 14195
    Prev
    Next
    INDEX
    Explanations

    mas grading

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

    code or foreign scripts

    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
     ഹോളി
    0.44
    ショー
    0.42
     डिस्टेंस
    0.40
    লিউ
    0.39
    鹘
    0.39
     चेंजेस
    0.38
     हिटलर
    0.38
    část
    0.37
    フィット
    0.36
    ेश्च
    0.36
    POSITIVE LOGITS
    گاه
    0.40
    айл
    0.39
    Linda
    0.39
    Lady
    0.39
    ᒎ
    0.39
    Murphy
    0.38
     রায়
    0.38
    ANTI
    0.38
    anti
    0.38
    DoesNotExist
    0.38
    Activations Density 0.297%

    No Known Activations