© 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. 75291
    Prev
    Next
    INDEX
    Explanations

    potential future

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

    words starting with a

    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
    শেষে
    0.55
    slüman
    0.54
     deleniti
    0.53
     原子
    0.51
    də
    0.48
     ℝ
    0.48
     পরই
    0.47
     ("[
    0.47
     provenance
    0.47
     geschaffen
    0.46
    POSITIVE LOGITS
    ्य
    0.46
    क्र
    0.46
    on
    0.45
    รั
    0.44
    у
    0.44
    asset
    0.44
    elect
    0.41
    قب
    0.41
     ebb
    0.40
    독
    0.40
    Activations Density 0.000%

    No Known Activations