© 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. 120486
    Prev
    Next
    INDEX
    Explanations

    spatial extent and properties

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

    easily flexible GF integrated

    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
    =""/>
    0.48
     począ
    0.46
     ศ
    0.45
     urządzenia
    0.45
    ={`${
    0.45
     এজেন্ট
    0.45
     ต
    0.44
     kelahiran
    0.44
     niezbęd
    0.44
     investimentos
    0.44
    POSITIVE LOGITS
    Gur
    0.47
     Simpl
    0.42
    кей
    0.42
     conm
    0.42
    Petit
    0.41
    票
    0.41
     Hask
    0.41
     disting
    0.40
    mique
    0.40
    就很
    0.40
    Activations Density 0.000%

    No Known Activations