© 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. 51657
    Prev
    Next
    INDEX
    Explanations

    Ctrl++, Virgin Mary, user opinions

    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
    型
    0.50
    }}$
    0.48
    、
    0.47
     variável
    0.46
     máxima
    0.46
     нуле
    0.46
    ブレーキ
    0.45
    위원회
    0.45
    우
    0.45
    マ
    0.44
    POSITIVE LOGITS
    ඡ
    0.54
     Portrait
    0.46
    uisine
    0.46
     Paraguay
    0.41
     σημ
    0.41
    hesu
    0.40
    foregroundView
    0.39
    imageNamed
    0.39
     Painter
    0.39
    hava
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.