© 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. 35459
    Prev
    Next
    INDEX
    Explanations

    puppetry. leaves

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

    high levels and changes

    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
    濂
    0.50
    使命
    0.48
    控
    0.45
    鹦
    0.43
    riding
    0.43
    bergh
    0.43
    iklet
    0.42
    鸚
    0.42
    릉
    0.42
    亚马
    0.41
    POSITIVE LOGITS
    ജെ
    0.58
     ethnicity
    0.53
     brokerage
    0.53
     impuls
    0.51
     fraîche
    0.51
     tez
    0.49
     muita
    0.48
     ต้น
    0.48
     साझे
    0.48
     お客様
    0.48
    Activations Density 0.000%

    No Known Activations