© 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. 58846
    Prev
    Next
    INDEX
    Explanations

    official information and procedures

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

    and other... / or other.

    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
    PROBLE
    0.49
    髀
    0.48
    េ
    0.48
     вероятно
    0.47
    ри
    0.46
     ю
    0.45
     ความ
    0.45
    Her
    0.44
    ה
    0.44
    riva
    0.44
    POSITIVE LOGITS
     autocl
    0.50
    स्टिक
    0.49
     Wochschr
    0.49
     initiative
    0.48
     اختی
    0.47
     pouches
    0.47
    inations
    0.46
     procedures
    0.46
     Init
    0.46
     helicopters
    0.45
    Activations Density 0.000%

    No Known Activations