© 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. 47882
    Prev
    Next
    INDEX
    Explanations

    starting enrollment transition

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

    enrollment and starting

    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
    谲
    0.51
    谥
    0.46
    门户
    0.44
     존
    0.44
     세계
    0.44
    çok
    0.43
    ீ
    0.43
    缺乏
    0.42
    政治
    0.42
     ಅಥವಾ
    0.42
    POSITIVE LOGITS
     staples
    0.56
     quitting
    0.56
     enrolling
    0.55
     starting
    0.51
     enroll
    0.50
     transitioning
    0.50
     eligibility
    0.49
     started
    0.49
     trekking
    0.48
     enrollment
    0.48
    Activations Density 0.000%

    No Known Activations