© 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. 109821
    Prev
    Next
    INDEX
    Explanations

    collection and use

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

    continued existence

    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
    I
    0.51
    ių
    0.47
    ی
    0.47
     左
    0.46
    }}
    0.45
    Fn
    0.45
    に
    0.45
    NASDAQ
    0.45
    u
    0.45
    を表
    0.44
    POSITIVE LOGITS
    шите
    0.47
    嘜
    0.46
    ंकी
    0.46
     возмо
    0.46
    还会
    0.44
    তিরিক্ত
    0.43
    还要
    0.43
     vzděl
    0.43
    ުމ
    0.43
     Mahi
    0.43
    Activations Density 0.000%

    No Known Activations