© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178900
    Prev
    Next
    INDEX
    Explanations

    business and activity

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

    specialized terms and punctuation

    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
    кен
    0.47
     invoke
    0.46
     Loaded
    0.44
     Planets
    0.44
    仪
    0.44
     Fc
    0.43
    يط
    0.43
     Array
    0.43
     Cell
    0.42
     Ember
    0.42
    POSITIVE LOGITS
     주의
    0.54
     剤
    0.54
     pernicious
    0.51
     photocopying
    0.51
     urination
    0.50
     extradition
    0.50
     ჩატი
    0.50
     바꾸
    0.49
     fabricating
    0.49
     inhaling
    0.49
    Activations Density 0.000%

    No Known Activations