© 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. 21052
    Prev
    Next
    INDEX
    Explanations

    we get

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

    Hey, Trap

    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
     キッズ
    0.47
     જોડાય
    0.47
    ğı
    0.45
    Ձ
    0.43
    흙
    0.43
    ὡ
    0.43
    肌
    0.42
     giriş
    0.41
     çalışma
    0.41
    ك
    0.41
    POSITIVE LOGITS
    mitter
    0.47
    sequences
    0.44
    auft
    0.43
    installer
    0.43
     resistor
    0.41
     communism
    0.41
    াউন্ড
    0.40
     quieran
    0.40
     installiert
    0.39
     heraus
    0.39
    Activations Density 0.000%

    No Known Activations