© 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. 14864
    Prev
    Next
    INDEX
    Explanations

    forms of 'is' or 'it'

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

    step by step with

    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
    ังกฤษ
    0.31
    verläss
    0.31
     Lembrando
    0.31
    碴
    0.30
     오늘의
    0.29
     ១
    0.29
    -%
    0.29
    âteaux
    0.29
    裡的
    0.29
    ärer
    0.29
    POSITIVE LOGITS
    t
    0.44
     the
    0.42
    l
    0.42
    the
    0.39
    r
    0.36
    c
    0.33
    U
    0.33
    f
    0.33
    e
    0.32
     they
    0.32
    Activations Density 0.194%

    No Known Activations