© 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. 150712
    Prev
    Next
    INDEX
    Explanations

    youth forums and activities

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

    future, problems, statistics, agents

    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
    ற்கான
    0.46
    apatillas
    0.45
    设
    0.44
    ర్భ
    0.43
     Receivable
    0.41
    解决
    0.41
    డవ
    0.40
    很大的
    0.39
     связан
    0.39
     Examining
    0.39
    POSITIVE LOGITS
     อี
    0.50
    Ș
    0.49
    آن
    0.49
     potenza
    0.48
     estuvo
    0.48
     ấn
    0.48
     copol
    0.48
     bottlene
    0.48
     angolo
    0.48
     tangente
    0.47
    Activations Density 0.000%

    No Known Activations