© 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. 78367
    Prev
    Next
    INDEX
    Explanations

    rights and responsibilities

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

    exploiting political power or weakness

    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
    Formation
    0.49
    ุม
    0.47
    Ammo
    0.45
    Combat
    0.45
    Rés
    0.44
    Findings
    0.44
    site
    0.43
    ח
    0.42
    Homepage
    0.42
    Comunic
    0.42
    POSITIVE LOGITS
     unicorns
    0.55
     trains
    0.52
     unicorn
    0.50
     presidents
    0.48
     Merle
    0.48
     councils
    0.47
     ministers
    0.47
     governed
    0.47
     overarching
    0.47
     enforcing
    0.46
    Activations Density 0.001%

    No Known Activations