© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 184300
    Prev
    Next
    INDEX
    Explanations

    back again

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

    introductions and beginnings

    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
    ადგენ
    0.59
     эксперти
    0.52
    敤
    0.50
    curité
    0.50
     Collectively
    0.50
     कॉ
    0.49
    胺
    0.49
    Specificity
    0.48
    ить
    0.46
     Commence
    0.46
    POSITIVE LOGITS
    ;
    0.57
    for
    0.54
    i
    0.51
    or
    0.49
    iky
    0.47
    hu
    0.47
     kop
    0.46
    em
    0.46
    old
    0.46
    ikus
    0.46
    Activations Density 0.001%

    No Known Activations