© 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. 152506
    Prev
    Next
    INDEX
    Explanations

    actuary

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

    arguments, explanations, outlines

    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
    conf
    0.55
    ands
    0.53
     (\%)
    0.51
    t
    0.51
    ese
    0.50
     payload
    0.49
    -(\
    0.49
    ando
    0.48
     animal
    0.47
    ר
    0.47
    POSITIVE LOGITS
    ْل
    0.52
    主に
    0.50
    🛁
    0.50
     Kommunikation
    0.50
     Sprachen
    0.49
     životu
    0.49
     sürekli
    0.47
    чак
    0.47
    荏
    0.46
    🌃
    0.46
    Activations Density 0.001%

    No Known Activations