© 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. 196364
    Prev
    Next
    INDEX
    Explanations

    warranty, Hockney, always aware, Newman completes

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

    successfully demonstratedbreathing rateincredibly difficult

    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
     cathodic
    0.54
     intermittent
    0.54
     differentiation
    0.52
     about
    0.50
     differentiating
    0.49
    ر
    0.48
     :-
    0.48
     auxiliary
    0.47
     undefined
    0.47
     Hanoi
    0.47
    POSITIVE LOGITS
    ພັນ
    0.55
     Kxa
    0.50
    サスカ
    0.49
    льника
    0.48
     ಸದ
    0.47
    拂
    0.47
    廷
    0.46
    жай
    0.46
    넋
    0.46
     ডাকে
    0.46
    Activations Density 0.000%

    No Known Activations