© 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. 177628
    Prev
    Next
    INDEX
    Explanations

    discover a range of reports

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

    technical explanations and code

    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
     bunches
    0.57
    谄
    0.47
    เฟ
    0.45
    畑
    0.43
     করব
    0.43
     gird
    0.43
     inclusions
    0.42
    Bunch
    0.42
     Dray
    0.42
     مهر
    0.41
    POSITIVE LOGITS
     অনুভূত
    0.42
     liye
    0.42
    ova
    0.41
    urta
    0.41
     우리
    0.40
    κ
    0.40
    ayeva
    0.40
    iagn
    0.40
    oa
    0.39
    <0xB3>
    0.39
    Activations Density 0.000%

    No Known Activations