© 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. 104185
    Prev
    Next
    INDEX
    Explanations

    place of, praising both, end to, merely an, offending others, raising questions, convention isn't

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

    These are unique alternatives

    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
    GYPT
    0.49
     aastal
    0.46
     antics
    0.43
    Earlier
    0.42
    YEAR
    0.41
     mwaka
    0.41
    ॅ
    0.41
    琨
    0.41
    пси
    0.40
     Inbetriebnahme
    0.40
    POSITIVE LOGITS
     这些
    0.55
     hoặc
    0.50
    这些
    0.48
     အရ
    0.46
     veya
    0.45
     accessibles
    0.44
    oks
    0.44
     निश्चित
    0.44
     accessible
    0.43
    分别
    0.43
    Activations Density 0.000%

    No Known Activations