© 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. 71772
    Prev
    Next
    INDEX
    Explanations

    Endocannabinoid System

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

    systemic failures

    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
    zei
    0.48
    Chooser
    0.44
     deinen
    0.44
    ѝ
    0.44
    ുപത്രി
    0.42
     deinem
    0.42
    贷
    0.42
    canc
    0.41
     Versand
    0.41
    แพทย์
    0.40
    POSITIVE LOGITS
     submerged
    0.48
     surrounded
    0.44
     municipales
    0.43
     lowland
    0.43
     dismantled
    0.43
     sensitivities
    0.42
    allen
    0.42
    ங்களில்
    0.42
     subcontinent
    0.41
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.41
    Activations Density 0.000%

    No Known Activations