© 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. 104639
    Prev
    Next
    INDEX
    Explanations

    young, recoverable, help, Sad, laughing

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

    notes and clarifications

    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
    fdPar
    0.53
    striatis
    0.49
    टि
    0.49
    seventh
    0.49
    imas
    0.48
    ියාව
    0.47
    ઇ
    0.47
    변경된
    0.46
    cesz
    0.46
    suivant
    0.46
    POSITIVE LOGITS
     constitutes
    0.51
     Diagram
    0.50
     Performance
    0.49
     Functions
    0.46
     klass
    0.46
     Documentation
    0.45
     Our
    0.45
     Bounds
    0.45
     ARN
    0.44
     B
    0.44
    Activations Density 0.000%

    No Known Activations