© 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. 62437
    Prev
    Next
    INDEX
    Explanations

    Christmas Carol Charades

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

    detection and surveillance

    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
    بە
    0.50
     możliwości
    0.46
    ਸ
    0.45
     வாழ
    0.44
     mám
    0.44
     colorChoice
    0.43
    MODEL
    0.43
    পরিস
    0.43
    。
    0.43
    ম
    0.42
    POSITIVE LOGITS
     NIST
    0.51
    geant
    0.49
    helmet
    0.49
    ien
    0.49
     orig
    0.48
     Buildable
    0.47
    umenical
    0.46
     Applicants
    0.46
    en
    0.44
     филосо
    0.44
    Activations Density 0.000%

    No Known Activations