© 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. 77065
    Prev
    Next
    INDEX
    Explanations

    look forward to

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

    context-dependent explanations

    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
     buildup
    0.49
     materially
    0.47
    ู
    0.46
    ामध्ये
    0.46
    <unused2140>
    0.45
    ड़ा
    0.44
    ഷണ
    0.44
     $+
    0.43
     hohe
    0.43
    ্ট
    0.43
    POSITIVE LOGITS
    l
    0.52
     Observ
    0.48
     કારણે
    0.46
     εν
    0.45
    ekan
    0.45
     Composer
    0.45
    pse
    0.45
    c
    0.44
     ऑन
    0.42
     ODE
    0.42
    Activations Density 0.001%

    No Known Activations