© 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. 174980
    Prev
    Next
    INDEX
    Explanations

    be used solely

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

    augmentation term that sums them

    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
    <unused94>
    0.59
     ສຳ
    0.58
     sukces
    0.58
     succès
    0.54
     alterna
    0.54
     reuni
    0.52
     problemy
    0.52
     produire
    0.51
     rozwią
    0.50
     illustrate
    0.50
    POSITIVE LOGITS
    aus
    0.46
    Guardian
    0.39
     до
    0.38
    гром
    0.38
    hooting
    0.38
    倦
    0.38
    笨
    0.37
     x
    0.37
    Von
    0.37
    edas
    0.37
    Activations Density 0.000%

    No Known Activations