© 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. 120730
    Prev
    Next
    INDEX
    Explanations

    controls, levels, meetings, office

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

    operating system components

    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
    "
    0.50
     Ide
    0.45
    ;
    0.44
     z
    0.43
     literature
    0.43
    、
    0.42
    0.42
    belt
    0.41
    dwell
    0.41
    ceptor
    0.41
    POSITIVE LOGITS
     рішення
    0.57
     واضح
    0.56
     פר
    0.54
    埛
    0.53
     руху
    0.52
     чисто
    0.50
     відео
    0.50
     수익
    0.49
     бро
    0.49
     ಬಂದ
    0.49
    Activations Density 0.001%

    No Known Activations