© 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. 12747
    Prev
    Next
    INDEX
    Explanations

    prefixes are

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

    Researchers tested, considering switching

    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
     גם
    0.40
     остальных
    0.40
    ALL
    0.39
    М
    0.39
    у
    0.38
    ALSO
    0.37
    аб
    0.37
    Ш
    0.36
     പിന്നീ
    0.36
    <unused664>
    0.35
    POSITIVE LOGITS
     @
    0.39
     @_
    0.38
     salah
    0.37
     sejumlah
    0.36
     kvůli
    0.36
     Hôm
    0.35
     #
    0.34
     tyrant
    0.34
     bulunmaktadır
    0.34
     pagoda
    0.33
    Activations Density 0.055%

    No Known Activations