© 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. 47817
    Prev
    Next
    INDEX
    Explanations

    but her that ali slide

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

    alphabetical word constraints

    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
     grop
    0.53
     equivariant
    0.47
     crawled
    0.44
     nostalgia
    0.44
     lonely
    0.44
     crawl
    0.44
     亠
    0.43
     片
    0.43
     nostalg
    0.43
     adaptor
    0.43
    POSITIVE LOGITS
    hello
    0.52
    these
    0.52
    etc
    0.47
     We
    0.46
     ইত্যা
    0.45
     কারনে
    0.44
    all
    0.43
     Hello
    0.43
    portions
    0.42
    Hello
    0.42
    Activations Density 0.000%

    No Known Activations