© 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. 104428
    Prev
    Next
    INDEX
    Explanations

    legal terms: prosecuted, reinstated

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

    questions about why

    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
    金属
    0.48
    ᱘
    0.45
    损失
    0.44
     métal
    0.44
    0.44
    传播
    0.43
    マグ
    0.43
     />}/>
    0.43
     trono
    0.42
     étrang
    0.42
    POSITIVE LOGITS
    enz
    0.58
    efficient
    0.54
    considering
    0.54
    all
    0.53
    voiced
    0.52
    algorithms
    0.51
    ell
    0.51
    lei
    0.51
    tiba
    0.51
    jitter
    0.50
    Activations Density 0.001%

    No Known Activations