© 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. 13801
    Prev
    Next
    INDEX
    Explanations

    we are, we're

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

    am an designed purpose

    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
    κολ
    0.50
     oppress
    0.47
     coseno
    0.46
     argomento
    0.46
     কর্মসূ
    0.45
     intimidate
    0.45
     rass
    0.44
    覇
    0.44
     zitten
    0.44
     estrange
    0.43
    POSITIVE LOGITS
     Society
    0.56
     Champions
    0.53
     Modern
    0.51
     World
    0.48
    ali
    0.47
     Dw
    0.47
     United
    0.47
     dwelling
    0.46
     relentless
    0.46
     Action
    0.46
    Activations Density 0.113%

    No Known Activations