© 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. 159365
    Prev
    Next
    INDEX
    Explanations

    new concepts and ideas

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

    what's new

    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
     वैक्सीन
    0.47
     टीकाकरण
    0.47
     sucre
    0.46
     ی
    0.46
    転車
    0.46
    츰
    0.45
     médicaments
    0.45
    ワクチン
    0.45
     promouvoir
    0.45
     déplacement
    0.45
    POSITIVE LOGITS
     I
    0.47
    i
    0.44
    cos
    0.43
     '
    0.43
    kak
    0.43
    ``
    0.42
     Kak
    0.42
    ''
    0.41
    """
    0.41
    gql
    0.40
    Activations Density 0.003%

    No Known Activations