© 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. 148620
    Prev
    Next
    INDEX
    Explanations

    whistleblower, event, disability, spirit

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

    kind of pain and disability

    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
     ouvrages
    0.54
     सॉरी
    0.50
     那麼
    0.49
    漯
    0.47
     पेशे
    0.47
     enchant
    0.47
    rainian
    0.46
    ruc
    0.46
    odore
    0.46
    cY
    0.45
    POSITIVE LOGITS
    า
    0.47
    Equity
    0.41
    ක්
    0.40
     Continue
    0.40
     constru
    0.40
    ències
    0.40
     specs
    0.40
     liners
    0.40
    が高
    0.39
     gritty
    0.39
    Activations Density 0.001%

    No Known Activations