© 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. 28887
    Prev
    Next
    INDEX
    Explanations

    transition from

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

    specific names or subjects

    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
    про
    0.47
    and
    0.47
    tk
    0.44
    Gra
    0.42
    담당
    0.42
    ʟ
    0.40
    moduleId
    0.40
    谨慎
    0.39
    batt
    0.39
    ucie
    0.38
    POSITIVE LOGITS
     設定
    0.58
     tiktok
    0.57
     kostenlos
    0.51
     ziehen
    0.51
     könnt
    0.50
     mnist
    0.50
     chihuahua
    0.49
     カラ
    0.49
    🫡
    0.49
     votar
    0.48
    Activations Density 0.000%

    No Known Activations