© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208481
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by non-english

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

    requires dependencies, notes, or setup

    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_262k_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
     fisica
    0.45
     ခ
    0.44
     Nimbus
    0.44
     strut
    0.44
    isi
    0.43
    ंख्य
    0.41
     enveloped
    0.41
     Str
    0.41
     större
    0.41
    foldername
    0.40
    POSITIVE LOGITS
     sacrifice
    0.46
    犧
    0.45
    స్తున్న
    0.45
    Runs
    0.44
     باست
    0.44
    匚
    0.44
    犠
    0.43
    Мен
    0.43
    遴
    0.43
    Ꮅ
    0.43
    Activations Density 0.001%

    No Known Activations