© 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. 233074
    Prev
    Next
    INDEX
    Explanations

    private wealth, connection with, job after

    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
     Proz
    0.55
     Latvia
    0.53
    v
    0.51
     Shear
    0.49
     Seeds
    0.49
     CHAS
    0.49
     PUP
    0.49
     Ā
    0.48
     SKAction
    0.47
     AdS
    0.46
    POSITIVE LOGITS
    亦
    0.47
     élections
    0.47
    講的是
    0.47
     aniversário
    0.46
    舉行
    0.46
    कार्यक्रम
    0.46
    GUNDABAD
    0.45
    archical
    0.45
    百年
    0.44
    ínio
    0.44
    Activations Density 0.001%

    No Known Activations