© 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. 78076
    Prev
    Next
    INDEX
    Explanations

    numbered list item followed by text

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

    commenting on quality or value

    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
    6
    0.50
     Despite
    0.46
    9
    0.45
     Lauder
    0.45
    \
    0.45
     reiter
    0.44
    $\
    0.44
    4
    0.44
     Auge
    0.43
    5
    0.42
    POSITIVE LOGITS
    চের
    0.46
    AnimationStyle
    0.44
     enteral
    0.42
     rotor
    0.42
     여러분
    0.40
     adop
    0.39
     程序
    0.39
     saree
    0.39
    ，”
    0.39
    Scheme
    0.38
    Activations Density 0.004%

    No Known Activations