© 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. 21109
    Prev
    Next
    INDEX
    Explanations

    use the

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

    Ghost features

    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
    6
    0.57
    8
    0.47
    7
    0.43
    ance
    0.42
     life
    0.42
    ور
    0.42
    み
    0.42
    ndt
    0.42
    <0xE1>
    0.41
    ну
    0.41
    POSITIVE LOGITS
     Arzneim
    0.59
     vaksin
    0.54
     오른
    0.50
     embroiled
    0.50
    лоти
    0.49
    猁
    0.49
     hippocamp
    0.48
     лекар
    0.48
    ASHINGTON
    0.47
     übernommen
    0.46
    Activations Density 0.000%

    No Known Activations