© 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. 191994
    Prev
    Next
    INDEX
    Explanations

    Siobhan, Christopher, Night

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

    minimum explains

    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
    contamination
    0.46
    empl
    0.43
    userName
    0.42
    piratory
    0.42
    ظل
    0.42
    proving
    0.41
    coating
    0.41
    粘
    0.41
    irrit
    0.41
    ulation
    0.41
    POSITIVE LOGITS
     isu
    0.49
     payoffs
    0.48
     معلومات
    0.47
     sought
    0.47
     nilai
    0.47
     informasi
    0.45
     између
    0.45
     défense
    0.45
     endereco
    0.45
     slew
    0.44
    Activations Density 0.002%

    No Known Activations