© 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. 168128
    Prev
    Next
    INDEX
    Explanations

    waiting for supply

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

    agency, choices, autonomy, willingness, change, mastery, workplace

    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
    bate
    0.48
    ()+
    0.47
    utilisateur
    0.46
    beams
    0.46
     hợp
    0.45
    autorité
    0.45
    FAC
    0.45
    جد
    0.44
    $-,
    0.44
    cuando
    0.44
    POSITIVE LOGITS
     Emirates
    0.52
     Merry
    0.52
     Swallow
    0.52
     gradual
    0.50
     Oceania
    0.50
     Daunting
    0.48
     Nitrogen
    0.47
     Backyard
    0.47
     Sunlight
    0.47
     Johannesburg
    0.47
    Activations Density 0.000%

    No Known Activations