© 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. 220042
    Prev
    Next
    INDEX
    Explanations

    affiliate links, shall behold, Jesus, toString

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

    expressing phrases or actions

    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
    活
    0.47
     ponctu
    0.46
    蝎
    0.46
    ave
    0.46
     ።
    0.45
    益
    0.45
    ኛ
    0.44
     أك
    0.44
    <0xA2>
    0.44
    棕
    0.43
    POSITIVE LOGITS
    i
    0.51
     desires
    0.49
    GRESS
    0.49
     skyscrapers
    0.47
     CHICAGO
    0.46
     cufflinks
    0.46
    PAC
    0.46
     miscon
    0.46
     CATALOG
    0.46
    руются
    0.45
    Activations Density 0.002%

    No Known Activations