© 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. 81142
    Prev
    Next
    INDEX
    Explanations

    continually do, supply voltage

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

    examples, features, ratings

    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
    កើត
    0.44
     orn
    0.42
     scourge
    0.40
     inzwischen
    0.39
    ต้อง
    0.39
    י
    0.38
    ..--
    0.38
     warns
    0.37
     auch
    0.37
     probes
    0.37
    POSITIVE LOGITS
     Leveraging
    0.46
     Plaza
    0.45
     المُ
    0.44
     αυτά
    0.44
     Attempts
    0.43
     utilizzati
    0.43
     trying
    0.43
    埥
    0.43
    isiä
    0.43
     Giving
    0.43
    Activations Density 0.003%

    No Known Activations