© 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. 224855
    Prev
    Next
    INDEX
    Explanations

    information and questions

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

    discussing lists, help, grind, recommendations, challenge

    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
     whistling
    0.46
     asesinato
    0.46
     pumping
    0.44
     tightening
    0.44
    tapping
    0.44
    उँ
    0.43
     demostrado
    0.43
    ４
    0.43
     murderer
    0.43
    کھوں
    0.43
    POSITIVE LOGITS
     Reviews
    0.54
    Review
    0.51
     جميع
    0.51
     Menu
    0.49
     Questions
    0.48
     উপদেশ
    0.47
     Ques
    0.47
     Review
    0.47
     гар
    0.46
     Zel
    0.46
    Activations Density 0.000%

    No Known Activations