© 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. 107684
    Prev
    Next
    INDEX
    Explanations

    now tell

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

    bugs and new features

    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
    and
    0.62
    w
    0.61
     as
    0.55
    into
    0.52
    labs
    0.51
    ibis
    0.49
    the
    0.49
    সে
    0.49
    jar
    0.48
    lz
    0.48
    POSITIVE LOGITS
     عادة
    0.47
    ):\
    0.47
     могат
    0.45
    anément
    0.45
    ాలంటే
    0.44
     ermöglichen
    0.43
     تريد
    0.43
    悭
    0.43
    Begriff
    0.43
     besitzen
    0.43
    Activations Density 0.001%

    No Known Activations