© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52323
    Prev
    Next
    INDEX
    Explanations

    Well, then, for the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $("
    0.47
     Kogi
    0.46
    Nigerian
    0.43
     comma
    0.42
    paragus
    0.41
    Niger
    0.41
     $,
    0.40
     herring
    0.40
    Several
    0.40
    ("/",
    0.40
    POSITIVE LOGITS
     ນ
    0.45
    瀟
    0.45
    াত্মক
    0.44
     तिच्या
    0.43
    াও
    0.42
    वर्स
    0.42
    دهای
    0.42
    啸
    0.40
    وپ
    0.40
    ever
    0.40
    Activations Density 0.003%

    No Known Activations