© 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. 169526
    Prev
    Next
    INDEX
    Explanations

    game or series decisions

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

    says probability

    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
     n
    0.50
     it
    0.49
     playbook
    0.46
     tiktok
    0.45
     धर्मशाला
    0.44
     able
    0.43
     tham
    0.43
     referral
    0.42
     scalable
    0.42
     private
    0.42
    POSITIVE LOGITS
    Completed
    0.52
    merz
    0.50
     чувство
    0.46
    Послед
    0.45
    Princeton
    0.44
    
    0.42
    Foreground
    0.42
    Toplam
    0.42
     Ио
    0.41
    Earnings
    0.41
    Activations Density 0.002%

    No Known Activations