© 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. 74965
    Prev
    Next
    INDEX
    Explanations

    personal liability insurance

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

    liability and its insurance coverage

    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
     pinnacle
    0.46
    M
    0.46
    titan
    0.44
     valiant
    0.44
    iked
    0.42
    Cs
    0.42
     me
    0.42
    ati
    0.42
     miserable
    0.42
    ignor
    0.42
    POSITIVE LOGITS
    泽
    0.54
    沚
    0.51
    洴
    0.50
     chiave
    0.49
    苾
    0.48
     spazio
    0.48
    䊂
    0.48
     españoles
    0.47
     SCALE
    0.47
     arası
    0.46
    Activations Density 0.006%

    No Known Activations