© 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. 105449
    Prev
    Next
    INDEX
    Explanations

    and the

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

    including options

    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
    female
    0.50
    b
    0.48
     female
    0.45
    o
    0.45
     southern
    0.44
     contributor
    0.44
    pard
    0.44
    us
    0.44
    drug
    0.44
    domain
    0.42
    POSITIVE LOGITS
     viktigt
    0.55
     మహ
    0.51
     otev
    0.50
     lezione
    0.48
    講
    0.48
     цього
    0.48
    وق
    0.48
     aquesta
    0.48
     infecting
    0.47
     когато
    0.47
    Activations Density 0.000%

    No Known Activations