© 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-65K
    7. 46784
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters

    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_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
    jší
    0.44
     Busy
    0.42
    (())
    0.41
    ding
    0.40
    |+
    0.40
     setzt
    0.39
     can
    0.39
    j
    0.39
    |
    0.39
    কের
    0.39
    POSITIVE LOGITS
     المياه
    0.48
     अँ
    0.47
    ?";
    0.47
    ...";
    0.46
     блоков
    0.46
     upland
    0.44
     υψη
    0.43
     multipurpose
    0.43
     ऑनर्स
    0.43
     반려동
    0.42
    Activations Density 0.005%

    No Known Activations