© 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. 222628
    Prev
    Next
    INDEX
    Explanations

    alias of, percent, king comforter cover, like a, tools to

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

    denying women property rights

    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
     &$\
    0.50
    nění
    0.50
    player
    0.48
    ovaní
    0.46
     নিঃসন্দেহে
    0.46
    &=&\
    0.45
    nj
    0.45
     まあ
    0.45
    mana
    0.45
    []>
    0.45
    POSITIVE LOGITS
    इससे
    0.54
    Ricardo
    0.51
    Research
    0.48
    Vi
    0.47
    Francesco
    0.47
    Virtual
    0.47
    Concern
    0.47
    ቴክ
    0.47
    Untuk
    0.46
     retrospect
    0.46
    Activations Density 0.000%

    No Known Activations