© 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. 33251
    Prev
    Next
    INDEX
    Explanations

    materials and construction

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

    succulent elegant Dave

    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
    нер
    0.44
     apartado
    0.44
    ាប់
    0.43
     پایان
    0.43
     अधिग्रहण
    0.41
    графия
    0.41
    奂
    0.40
     графика
    0.40
    涣
    0.39
    нде
    0.39
    POSITIVE LOGITS
    fitting
    0.46
    sto
    0.44
    tris
    0.42
     stoichi
    0.42
     zus
    0.41
    con
    0.41
    pod
    0.41
    chym
    0.41
    jane
    0.39
     meestal
    0.39
    Activations Density 0.000%

    No Known Activations