© 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. 4551
    Prev
    Next
    INDEX
    Explanations

    contractions followed by verbs or adjectives

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

    been feeling

    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
    s
    1.08
    ों
    1.07
    $,
    0.95
    ς
    0.94
    tedir
    0.87
    r
    0.87
    y
    0.87
    ים
    0.86
    m
    0.82
    ses
    0.82
    POSITIVE LOGITS
    ン
    0.93
     Been
    0.89
     been
    0.86
    Been
    0.84
    been
    0.84
    ન
    0.77
    न
    0.77
    ır
    0.71
    ن
    0.71
     gotta
    0.70
    Activations Density 0.654%

    No Known Activations