© 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. 235751
    Prev
    Next
    INDEX
    Explanations

    Nanny or legal obligations

    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
     hinders
    0.55
     impede
    0.51
     ､
    0.50
     impide
    0.50
     interacts
    0.49
     initializes
    0.49
     discerned
    0.48
     weakens
    0.48
     කරයි
    0.47
     inhibits
    0.46
    POSITIVE LOGITS
    B
    0.48
     kres
    0.47
     cu
    0.45
     kendi
    0.45
    V
    0.44
    Romeo
    0.43
    كل
    0.43
    كلم
    0.43
    اتج
    0.43
    products
    0.43
    Activations Density 0.000%

    No Known Activations