© 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. 8881
    Prev
    Next
    INDEX
    Explanations

    as well as

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

    as this

    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
     如果
    0.34
    ’
    0.32
     แบ่ง
    0.31
    :
    0.30
     อีก
    0.29
    AGE
    0.29
    鵰
    0.29
    }-\
    0.28
     บอก
    0.28
    ByURL
    0.28
    POSITIVE LOGITS
     it
    0.55
    it
    0.43
     a
    0.42
     we
    0.41
    a
    0.41
     he
    0.39
    t
    0.38
     this
    0.37
    sembles
    0.37
     evidenced
    0.37
    Activations Density 0.341%

    No Known Activations