© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 136911
    Prev
    Next
    INDEX
    Explanations

    discussing specific origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    很久
    0.48
    눠
    0.46
    <unused80>
    0.42
    プラ
    0.41
    НУ
    0.39
     البسط
    0.38
    ruppen
    0.38
    તાઓ
    0.38
    接地
    0.38
    ◤
    0.37
    POSITIVE LOGITS
     Discussion
    0.46
     olfactory
    0.45
     특정
    0.44
     specific
    0.43
     ($
    0.42
     taste
    0.42
     discussion
    0.42
     origin
    0.42
     Origin
    0.42
     Sub
    0.41
    Activations Density 0.002%

    No Known Activations