© 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. 139144
    Prev
    Next
    INDEX
    Explanations

    further information

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

    notes linkingorfear was tight

    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
    𝘼
    0.51
    bentuk
    0.48
    wissenschaft
    0.48
    usak
    0.47
    kait
    0.47
    wari
    0.46
     అయితే
    0.45
    hong
    0.45
     ರಿಂದ
    0.45
    iyor
    0.45
    POSITIVE LOGITS
     flights
    0.49
     $|
    0.48
     Local
    0.46
     masonry
    0.46
    াড়
    0.46
    تمر
    0.46
     Flights
    0.45
     Lu
    0.44
     خپل
    0.44
     spacer
    0.43
    Activations Density 0.000%

    No Known Activations