© 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. 57274
    Prev
    Next
    INDEX
    Explanations

    speech, text, or information following certain punctuation

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

    setting up, before, delay

    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
     आटे
    0.61
     被
    0.57
     ἐν
    0.57
     得
    0.56
     위해서
    0.52
     カラ
    0.52
     起
    0.51
     머
    0.50
     除了
    0.50
     можа
    0.50
    POSITIVE LOGITS
    ,
    0.54
    (
    0.52
    Errors
    0.51
    Result
    0.49
    Is
    0.49
    Youth
    0.49
    Where
    0.48
    Version
    0.48
    Ellis
    0.46
    Field
    0.46
    Activations Density 0.000%

    No Known Activations