© 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. 184248
    Prev
    Next
    INDEX
    Explanations

    warnings and instructions

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

    prepare for all conditions

    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
     zerst
    0.56
     föld
    0.52
    Hurricane
    0.52
    hurricane
    0.51
     devastation
    0.50
    保护
    0.49
    赈
    0.49
    災害
    0.49
     disasters
    0.48
     protezione
    0.47
    POSITIVE LOGITS
     unnecessary
    0.47
     Strongly
    0.46
     light
    0.45
     Spice
    0.44
    があれば
    0.43
     consume
    0.42
     Refresh
    0.42
     Slow
    0.42
     радио
    0.42
     Drinks
    0.41
    Activations Density 0.042%

    No Known Activations