© 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. 237520
    Prev
    Next
    INDEX
    Explanations

    priorities and needs

    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
    )
    0.46
    ०
    0.46
    %>%
    0.45
    बे
    0.45
    न
    0.44
     পদ
    0.43
    zd
    0.43
    、$
    0.43
    wr
    0.43
     στιγ
    0.43
    POSITIVE LOGITS
    複雜
    0.46
     megfelel
    0.44
    ስቃሴ
    0.44
     Drought
    0.44
     Nación
    0.44
    泞
    0.44
    閎
    0.44
     simplic
    0.43
     uygun
    0.43
     Jú
    0.43
    Activations Density 0.001%

    No Known Activations