© 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. 57455
    Prev
    Next
    INDEX
    Explanations

    radiation, binding, added

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

    context window, maximize efficiency, bounty programs

    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
    Пет
    0.52
     ранее
    0.51
    ума
    0.51
    Можно
    0.49
    ковым
    0.49
    лиз
    0.49
    कई
    0.48
    प
    0.48
    피
    0.48
    Ꮟ
    0.48
    POSITIVE LOGITS
     orders
    0.44
     rum
    0.44
     occupational
    0.44
     ܘ
    0.43
     UC
    0.42
     Department
    0.41
     کام
    0.41
     až
    0.41
     olim
    0.41
     OL
    0.40
    Activations Density 0.000%

    No Known Activations