© 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. 14163
    Prev
    Next
    INDEX
    Explanations

    residential property

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

    end of phrases

    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
    नए
    0.29
    鲞
    0.29
    दिल्ली
    0.28
    缫
    0.28
    ரசுக்
    0.27
    ℚ
    0.27
    盉
    0.27
    ༸
    0.27
    सरकार
    0.27
    숲
    0.27
    POSITIVE LOGITS
     the
    0.37
     L
    0.31
     H
    0.31
     G
    0.30
     outliers
    0.30
     was
    0.30
     A
    0.30
     manly
    0.30
     S
    0.29
     a
    0.29
    Activations Density 0.106%

    No Known Activations