© 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. 80677
    Prev
    Next
    INDEX
    Explanations

    ever followed by verb

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

    ever followed by a past participle

    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
    ਾ
    1.00
    ется
    0.82
    ն
    0.79
    ες
    0.79
    اری
    0.77
    인다
    0.77
    ある
    0.76
    یم
    0.76
    ها
    0.75
    وٹی
    0.74
    POSITIVE LOGITS
    0
    1.09
    h
    0.97
     (
    0.92
    da
    0.87
    ne
    0.79
     in
    0.78
    na
    0.78
    name
    0.76
    K
    0.73
    .
    0.72
    Activations Density 0.156%

    No Known Activations