© 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. 256106
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     characteristics
    0.49
     deseas
    0.48
     cursing
    0.47
     الحركه
    0.46
    čk
    0.45
     môžete
    0.45
     ܥ
    0.43
     Doesn
    0.43
     dehuman
    0.43
     chcete
    0.43
    POSITIVE LOGITS
    AIR
    0.52
    Facade
    0.48
    (
    0.48
    air
    0.47
    income
    0.46
    Air
    0.45
    aire
    0.45
    DX
    0.44
    astica
    0.43
    abilă
    0.43
    Activations Density 0.001%

    No Known Activations