© 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. 62886
    Prev
    Next
    INDEX
    Explanations

    company profiles and experience

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

    Walker, Texas Ranger; ncurses; learnings

    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
    queryString
    0.49
     Minerals
    0.48
    式的
    0.48
     Algebraic
    0.47
     Medicines
    0.46
     化学
    0.46
    级别的
    0.46
    C
    0.46
     Masters
    0.44
    showAlert
    0.44
    POSITIVE LOGITS
     berhenti
    0.48
     bermain
    0.47
    ल्डर
    0.46
     karoti
    0.46
     mendapat
    0.46
     palav
    0.46
     connotations
    0.46
     saranam
    0.46
     menambah
    0.45
     adver
    0.45
    Activations Density 0.000%

    No Known Activations