© 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. 60124
    Prev
    Next
    INDEX
    Explanations

    fort committing

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

    consent, respect, arousal

    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
     concetto
    0.54
    鿌
    0.51
     formée
    0.50
     stöd
    0.50
     conceito
    0.49
     udrž
    0.49
     både
    0.48
     élast
    0.48
     composée
    0.48
     школи
    0.48
    POSITIVE LOGITS
    class
    0.50
    name
    0.46
     fatally
    0.46
    vacuum
    0.45
    photon
    0.45
     revenge
    0.44
    d
    0.44
    cell
    0.44
    pair
    0.43
    summary
    0.43
    Activations Density 0.001%

    No Known Activations