© 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. 137047
    Prev
    Next
    INDEX
    Explanations

    effective, successful, preserves

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

    describing abstract concepts and actions

    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
     नए
    0.45
    ירות
    0.44
     yapılacak
    0.42
     bubbles
    0.41
     नये
    0.41
    標
    0.41
    ited
    0.41
    ావ
    0.40
    值得
    0.40
    ESI
    0.40
    POSITIVE LOGITS
     Yvonne
    0.46
     ब्लाइंड
    0.46
     Waren
    0.44
    norm
    0.44
     Australia
    0.44
     persönlichen
    0.44
     gesetz
    0.43
    盥
    0.43
     congén
    0.42
    thern
    0.42
    Activations Density 0.000%

    No Known Activations