© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 153848
    Prev
    Next
    INDEX
    Explanations

    reasons for places

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

    often followed by stop or exit

    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
    resent
    0.49
    öld
    0.44
    \|^{
    0.44
    ün
    0.43
    ulp
    0.43
     unaccount
    0.43
     sexes
    0.42
     трав
    0.42
     అనంతరం
    0.42
     қол
    0.41
    POSITIVE LOGITS
    east
    0.54
    பாடு
    0.48
    ه‌ی
    0.48
    дый
    0.46
    克
    0.46
    getBounding
    0.45
    दय
    0.45
    o
    0.44
    ତି
    0.44
    ascending
    0.44
    Activations Density 0.000%

    No Known Activations