© 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. 190405
    Prev
    Next
    INDEX
    Explanations

    per day

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

    crumbling, collapsed, falling apart

    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
    0.57
    ’
    0.52
    $\
    0.47
     injustices
    0.46
     resto
    0.46
    أ
    0.46
     clientes
    0.45
    ų
    0.44
    </strong>
    0.44
     altri
    0.44
    POSITIVE LOGITS
    UPA
    0.48
     сов
    0.47
    шым
    0.47
     рез
    0.47
     同时
    0.46
     హైదర్
    0.46
    谲
    0.46
     совпада
    0.46
    खिक
    0.44
     терро
    0.44
    Activations Density 0.000%

    No Known Activations