© 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. 186679
    Prev
    Next
    INDEX
    Explanations

    rewrite process, morning start, youtube semiconductor

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

    list formatting and code examples

    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
    P
    0.44
     zle
    0.43
     recep
    0.43
     dịp
    0.43
     kí
    0.42
    T
    0.42
     lejos
    0.42
     Intelligent
    0.41
     zeroth
    0.41
    我们
    0.41
    POSITIVE LOGITS
    oses
    0.51
    రించి
    0.51
    ร้อม
    0.48
     मुद्रा
    0.48
    /";
    0.47
    𒁲
    0.47
     நோக்கி
    0.47
    <unused25>
    0.46
     माँ
    0.46
    นาด
    0.46
    Activations Density 0.000%

    No Known Activations