© 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. 6272
    Prev
    Next
    INDEX
    Explanations

    online planning

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

    identifying potential odors

    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
     mechanism
    0.48
    勬
    0.45
     وبي
    0.44
    يلا
    0.43
     sucess
    0.43
    寶
    0.43
     rodent
    0.43
     dedic
    0.42
     enjoyable
    0.42
     SECOND
    0.42
    POSITIVE LOGITS
    applique
    0.52
    捙
    0.50
    plier
    0.50
    ukka
    0.49
     絵
    0.49
    issors
    0.48
     Manik
    0.48
     झटका
    0.47
     Lichten
    0.46
    ängel
    0.46
    Activations Density 0.000%

    No Known Activations