© 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. 71990
    Prev
    Next
    INDEX
    Explanations

    URLs, journalism, minister

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

    fundamentally remain

    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
     jums
    0.47
     назем
    0.46
     j
    0.45
    ạn
    0.44
    זה
    0.44
     emocionante
    0.44
     intel
    0.44
    ■
    0.44
    ționale
    0.43
     propriet
    0.43
    POSITIVE LOGITS
     unaware
    0.47
    пова
    0.46
     phenytoin
    0.46
     فضای
    0.45
     appellee
    0.44
    幼儿
    0.44
    risi
    0.43
     edging
    0.42
     withdrawing
    0.42
     नव
    0.41
    Activations Density 0.002%

    No Known Activations