© 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. 12146
    Prev
    Next
    INDEX
    Explanations

    question mark followed by name

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

    questions ending in questions

    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
    締め
    0.44
    満足
    0.44
    想法
    0.42
     ((*
    0.41
    lems
    0.41
    吉
    0.41
     প্রণাম
    0.40
    忥
    0.40
    latego
    0.40
     आश्वासन
    0.39
    POSITIVE LOGITS
     asks
    0.82
     asked
    0.76
    asked
    0.69
     inquired
    0.67
     preguntó
    0.65
     question
    0.62
    ?'
    0.61
     पूछता
    0.61
    asks
    0.61
     wondered
    0.60
    Activations Density 0.012%

    No Known Activations