© 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. 147861
    Prev
    Next
    INDEX
    Explanations

    special occasions

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

    especially with loads, lost during, small power

    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
     are
    0.50
    烽
    0.46
    ⚔
    0.45
    を獲得
    0.44
    狼
    0.43
     сложно
    0.43
     estrella
    0.43
    ダ
    0.43
     vortex
    0.43
     Times
    0.43
    POSITIVE LOGITS
    bank
    0.46
    coefficient
    0.46
    park
    0.45
    currentUser
    0.45
     행사
    0.44
    wyczaj
    0.44
    param
    0.43
     participatory
    0.43
    coeff
    0.43
    candidates
    0.43
    Activations Density 0.001%

    No Known Activations