© 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. 104937
    Prev
    Next
    INDEX
    Explanations

    country transactions

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

    without downtime or performance degradation

    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
    ی
    0.49
    s
    0.47
     grind
    0.46
    轎
    0.45
    Nem
    0.43
     zal
    0.43
     lan
    0.42
     cater
    0.42
    Sz
    0.41
     millas
    0.41
    POSITIVE LOGITS
    悛
    0.50
     Balliye
    0.49
     받고
    0.48
     ਕੀਤਾ
    0.48
    elevationMap
    0.47
     देखील
    0.47
    ご了承
    0.47
    ripty
    0.47
     जोकि
    0.46
     ประกอบ
    0.46
    Activations Density 0.001%

    No Known Activations