© 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. 196607
    Prev
    Next
    INDEX
    Explanations

    or however though

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

    puzzle and connects

    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
    となる
    0.42
    arXiv
    0.42
    $\
    0.40
     Adverse
    0.40
     genomes
    0.40
    )}$
    0.39
    uuid
    0.39
     continua
    0.39
     rendah
    0.39
     dystopian
    0.39
    POSITIVE LOGITS
     বোল
    0.44
    锉
    0.42
    砼
    0.42
     wooden
    0.42
    巉
    0.41
     Venetian
    0.41
     mandrel
    0.41
    秫
    0.41
     triglyceride
    0.41
    木
    0.40
    Activations Density 0.000%

    No Known Activations