© 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. 104298
    Prev
    Next
    INDEX
    Explanations

    sentence fragments preceding names

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

    maximizes within a radius

    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
    里
    0.65
     裏
    0.50
    的這個
    0.48
    隔離
    0.47
    這裡
    0.47
    ях
    0.46
    વવા
    0.46
    ş
    0.46
    ями
    0.46
    鯤
    0.45
    POSITIVE LOGITS
     Rober
    0.50
     admires
    0.50
    nT
    0.48
     inquiring
    0.47
     destroys
    0.47
     angered
    0.47
     Utilis
    0.46
    nig
    0.46
    scri
    0.46
     apprendre
    0.46
    Activations Density 0.001%

    No Known Activations