© 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. 100952
    Prev
    Next
    INDEX
    Explanations

    tangram Bible disadvantaged Vanguard stocks

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

    violence, sex, technical, dates, food, science

    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
    igraf
    0.46
    στή
    0.46
    首次
    0.45
    environnement
    0.44
     P
    0.43
    꼽
    0.43
    SVG
    0.43
     xwe
    0.42
     memoria
    0.41
     वातावरण
    0.41
    POSITIVE LOGITS
                    
    0.47
     stumbling
    0.46
    ),\
    0.46
     decreases
    0.46
     geändert
    0.45
     wasn
    0.44
     lessened
    0.42
     unfolds
    0.42
    $[\
    0.42
     rozwiąz
    0.42
    Activations Density 0.000%

    No Known Activations