© 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. 135551
    Prev
    Next
    INDEX
    Explanations

    media, actors, collaboration, outlets

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

    drug use, network issue, keyboard, vehicle, corporations

    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
    t
    0.57
    uigen
    0.48
    switching
    0.46
    z
    0.46
    failure
    0.46
    exposure
    0.45
    conventional
    0.44
     exhibited
    0.43
    တော့
    0.43
     entrepreneurs
    0.42
    POSITIVE LOGITS
     zostanie
    0.47
    녠
    0.46
    }^{*}$.
    0.46
     SHO
    0.45
    ربعة
    0.45
    臾
    0.45
     monoxide
    0.44
     DIRECT
    0.44
     被
    0.44
    向下
    0.43
    Activations Density 0.000%

    No Known Activations