© 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. 130662
    Prev
    Next
    INDEX
    Explanations

    Digital marketing campaigns

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

    fit transform

    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
     层
    0.50
    愿意
    0.49
     儿童
    0.44
    枪
    0.44
     shì
    0.43
     还
    0.43
    见面
    0.43
    剻
    0.43
     satisfacción
    0.42
    设计师
    0.41
    POSITIVE LOGITS
     automaton
    0.45
     THEIR
    0.44
     WE
    0.43
    вів
    0.40
     electr
    0.39
    वह
    0.39
    ᅳ
    0.39
    FR
    0.38
    ток
    0.38
     Santé
    0.38
    Activations Density 0.000%

    No Known Activations