© 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. 237353
    Prev
    Next
    INDEX
    Explanations

    words following punctuation or 'the'

    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
    𝐕
    0.53
    出于
    0.50
     bargains
    0.47
     deals
    0.46
     بدنا
    0.46
     نوم
    0.46
    DependentUpon
    0.45
     exerc
    0.45
    apparition
    0.45
    deals
    0.45
    POSITIVE LOGITS
     Trust
    0.52
     (
    0.51
     Trusts
    0.47
     Award
    0.47
     Per
    0.47
    ires
    0.46
     Diaspora
    0.46
     Europea
    0.46
     Lone
    0.46
     Atau
    0.46
    Activations Density 0.000%

    No Known Activations