© 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. 14440
    Prev
    Next
    INDEX
    Explanations

    numbers and states

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

    zero initialization

    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
     चालीस
    0.49
    䏹
    0.46
    ंच्या
    0.44
    धपुर
    0.44
     kulland
    0.44
     চল্লিশ
    0.44
    وب
    0.43
     மொத்த
    0.43
     ৪৮
    0.42
     Klar
    0.41
    POSITIVE LOGITS
     zero
    0.91
     zéro
    0.80
    zero
    0.71
     cero
    0.70
    ゼロ
    0.69
    ０
    0.69
     صفر
    0.68
    零
    0.67
     जीरो
    0.65
     нулю
    0.65
    Activations Density 0.018%

    No Known Activations