© 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. 120400
    Prev
    Next
    INDEX
    Explanations

    What kind or which

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

    asking what

    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
    Ꭻ
    0.50
     drugi
    0.49
     nöt
    0.48
     👌
    0.47
    orragie
    0.47
     دوم
    0.46
     ਕੇ
    0.46
     دي
    0.46
     meer
    0.46
    អំ
    0.46
    POSITIVE LOGITS
    든지
    0.48
    -
    0.47
    Secure
    0.46
    hen
    0.45
    ?
    0.44
    RA
    0.43
    よりも
    0.43
    ench
    0.42
    ons
    0.42
    to
    0.41
    Activations Density 0.007%

    No Known Activations