© 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-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 79116
    Prev
    Next
    INDEX
    Explanations

    text following punctuation

    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_53_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
     transcribed
    0.53
     Tessa
    0.51
     written
    0.48
    TxtArea
    0.47
    탠
    0.46
    tes
    0.46
     typed
    0.46
     plaintext
    0.46
     tessel
    0.46
     plain
    0.46
    POSITIVE LOGITS
     Text
    0.50
    text
    0.48
    Text
    0.46
     text
    0.41
    uld
    0.40
     Hui
    0.40
    лох
    0.40
    文
    0.40
     文
    0.37
     według
    0.36
    Activations Density 0.066%

    No Known Activations