© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15834
    Prev
    Next
    INDEX
    Explanations

    manner in which

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

    pointer to

    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_16k_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
    ج
    1.31
    ان
    1.18
    س
    1.18
    ق
    1.15
    ش
    1.13
    ম
    1.05
    )。
    1.03
    이
    1.01
    م
    0.99
    ก
    0.97
    POSITIVE LOGITS
    r
    0.86
    idge
    0.85
    lijk
    0.85
    er
    0.83
    prise
    0.82
    ling
    0.80
    ially
    0.80
    phone
    0.80
    thing
    0.80
    hythm
    0.79
    Activations Density 4.710%

    No Known Activations