© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 167873
    Prev
    Next
    INDEX
    Explanations

    keeps cool

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

    constructivist idea, laws, direct referral

    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
    Negative Logits
     urldecode
    0.45
    去掉
    0.44
     美国
    0.44
     心
    0.43
     HSPB
    0.42
    adığı
    0.42
     डेवल
    0.42
    ଛି
    0.42
    akuan
    0.42
     güzel
    0.41
    POSITIVE LOGITS
    йна
    0.44
    Dix
    0.43
    \
    0.43
     العليا
    0.42
    Dip
    0.42
    ները
    0.41
    Direct
    0.41
     fech
    0.40
    llam
    0.40
    Commiss
    0.40
    Activations Density 0.001%

    No Known Activations