© 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. 43740
    Prev
    Next
    INDEX
    Explanations

    everyone and everything

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

    everything you need is

    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
     be
    0.98
    lL
    0.68
     as
    0.67
     terrib
    0.67
    ا۔
    0.67
     muut
    0.65
     feria
    0.62
    ల
    0.62
     années
    0.62
     llev
    0.61
    POSITIVE LOGITS
    0
    0.98
    in
    0.72
    ти
    0.72
    ０
    0.71
     G
    0.71
     W
    0.70
    те
    0.70
    <0x80>
    0.70
    ко
    0.69
     O
    0.68
    Activations Density 0.045%

    No Known Activations