© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38393
    Prev
    Next
    INDEX
    Explanations

    initial inquiry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ބ
    0.46
    botones
    0.45
    ボタン
    0.44
    あん
    0.44
     リュ
    0.44
    時間に
    0.43
     回転
    0.42
    が変わ
    0.42
     کارت
    0.42
    t
    0.42
    POSITIVE LOGITS
     angeboten
    0.50
     elke
    0.49
     erfolgen
    0.48
     versa
    0.45
     forbindelse
    0.45
     tilby
    0.44
    äum
    0.44
     erfolgt
    0.44
    ţiei
    0.42
    uable
    0.42
    Activations Density 0.001%

    No Known Activations