© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13254
    Prev
    Next
    INDEX
    Explanations

    May fair, and vegetables

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

    locations or specific things

    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
    2
    0.31
     Mistakes
    0.30
    
    0.30
    5
    0.30
     Insulation
    0.29
    0
    0.29
    <eos>
    0.29
    flash
    0.29
     Once
    0.28
     ل
    0.28
    POSITIVE LOGITS
    Ყ
    0.35
     אר
    0.34
     двумя
    0.33
    ፨
    0.33
    訖
    0.33
    。"
    0.31
    IDENTIAL
    0.31
    rául
    0.31
     イエロー
    0.31
    츰
    0.31
    Activations Density 0.001%

    No Known Activations