© 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. 231442
    Prev
    Next
    INDEX
    Explanations

    activity and place descriptions

    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
     అనేది
    0.48
    נטי
    0.47
     handleClick
    0.46
     manifeste
    0.46
    --(
    0.44
     सजा
    0.44
    榱
    0.44
    鱔
    0.43
    編輯
    0.43
    тке
    0.43
    POSITIVE LOGITS
    ↵
    0.48
    Tor
    0.45
     Großbritannien
    0.43
     arrivée
    0.43
     Confidential
    0.43
     illetve
    0.42
     Ergebnis
    0.42
     Verhalten
    0.41
     tor
    0.40
     économiques
    0.40
    Activations Density 0.002%

    No Known Activations