© 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. 182355
    Prev
    Next
    INDEX
    Explanations

    ability to not

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

    steps definition

    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
    ਾ
    0.48
    pessoas
    0.43
    uação
    0.43
     betrayed
    0.41
    не
    0.41
    ुअल
    0.41
    యే
    0.40
    ુ
    0.40
    vní
    0.40
    ан
    0.40
    POSITIVE LOGITS
     keeping
    0.39
     ክፍል
    0.39
     securing
    0.38
     permettre
    0.38
     perspiration
    0.38
     टेंशन
    0.38
     innovation
    0.38
    PosY
    0.37
     Atari
    0.37
     whose
    0.36
    Activations Density 0.000%

    No Known Activations