© 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. 216998
    Prev
    Next
    INDEX
    Explanations

    closing issues, RCA jacks, converted vans

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

    avoiding harmful limitations

    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
     ४
    0.52
     miracles
    0.50
     dumpling
    0.50
     فريبي
    0.49
     bookcase
    0.49
    ן
    0.49
    ѳ
    0.49
     其中
    0.48
     больш
    0.48
     بالنسبه
    0.47
    POSITIVE LOGITS
    sj
    0.43
    وسی
    0.41
     Tour
    0.41
    도를
    0.40
     assertFalse
    0.40
     equilibrio
    0.40
    倫
    0.40
    Kamp
    0.39
    Hey
    0.39
     épisode
    0.39
    Activations Density 0.000%

    No Known Activations