© 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. 24695
    Prev
    Next
    INDEX
    Explanations

    posted on date

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

    monster, strategically, cats, prematurely, Google

    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
    imam
    0.45
    cps
    0.45
    Charged
    0.44
    너
    0.44
    穗
    0.44
    nicht
    0.44
    니
    0.44
    Hyderabad
    0.43
    ільки
    0.43
    WOOD
    0.43
    POSITIVE LOGITS
     rubbing
    0.50
     abertura
    0.47
     gest
    0.45
     apertura
    0.45
     sliced
    0.44
     alcance
    0.44
     y
    0.43
     slicing
    0.43
    стрее
    0.43
     sodio
    0.43
    Activations Density 0.001%

    No Known Activations