© 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. 249962
    Prev
    Next
    INDEX
    Explanations

    specifying sequences

    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
    ION
    0.51
    IK
    0.49
    ING
    0.48
    ও
    0.48
    ROW
    0.47
    Ｉ
    0.45
    CHILD
    0.45
    PL
    0.44
    Ｆ
    0.44
    )^
    0.44
    POSITIVE LOGITS
     Classical
    0.48
     रक्ष
    0.47
     बुखार
    0.44
     Consideration
    0.44
     asian
    0.43
     Dirk
    0.43
     Autumn
    0.42
     اُ
    0.42
     tulips
    0.42
     eigens
    0.42
    Activations Density 0.001%

    No Known Activations