© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3188
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
    䚯
    0.85
     सीएचएसएल
    0.80
    㪇
    0.80
    <unused1738>
    0.80
    蟶
    0.80
    <unused231>
    0.78
    ὺς
    0.77
    <unused1666>
    0.76
    昍
    0.76
    琟
    0.76
    POSITIVE LOGITS
    <eos>
    3.73
    ៕
    2.11
    <end_of_turn>
    1.99
    ↵↵↵↵↵↵↵↵
    1.87
    ↵↵↵↵↵↵↵↵↵↵
    1.79
    ↵↵↵↵↵↵↵↵↵
    1.78
    ↵↵↵↵↵↵↵↵↵↵↵↵
    1.75
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.74
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.72
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.71
    Activations Density 0.707%

    No Known Activations