© 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. 4950
    Prev
    Next
    INDEX
    Explanations

    processes ending in ing

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

    processes and steps

    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
    σουμε
    0.47
    س
    0.47
    û
    0.47
    গ্রস্ত
    0.47
    ினர்
    0.47
    нской
    0.46
     পরিচাল
    0.46
    ный
    0.46
    ánk
    0.46
    ні
    0.45
    POSITIVE LOGITS
     of
    0.67
    /
    0.57
     that
    0.53
    -
    0.53
     yeasts
    0.51
    (
    0.51
     venues
    0.51
     paradigms
    0.51
    ЗИ
    0.51
    )
    0.50
    Activations Density 0.000%

    No Known Activations