© 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. 90351
    Prev
    Next
    INDEX
    Explanations

    we are

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

    cloud computing

    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
     Bunu
    0.50
    basically
    0.49
    ujar
    0.44
    
    0.44
    dalam
    0.44
     Bhand
    0.44
     शासित
    0.43
    dans
    0.43
    >:
    0.43
    mel
    0.43
    POSITIVE LOGITS
     persön
    0.50
     perte
    0.49
     Hayley
    0.49
     geriatric
    0.49
    之际
    0.49
     doświad
    0.48
     terrific
    0.46
    里程
    0.46
     osobow
    0.45
     iconography
    0.45
    Activations Density 0.001%

    No Known Activations