© 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-16K
    7. 11793
    Prev
    Next
    INDEX
    Explanations

    business priorityFacebook Analyticsincreasing orderice cream formquestions

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

    contexts and situations

    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_16k_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
    ใน
    0.55
     în
    0.54
    可在
    0.49
     в
    0.48
    在我
    0.48
     در
    0.48
    ในการ
    0.47
     στο
    0.47
     into
    0.46
     στην
    0.45
    POSITIVE LOGITS
     وفي
    0.84
     guise
    0.81
    看来
    0.79
    的基础上
    0.77
    的情况下
    0.75
    ၌
    0.69
     کې
    0.65
     midst
    0.63
    基础上
    0.63
     contexts
    0.61
    Activations Density 0.801%

    No Known Activations