© 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. 182428
    Prev
    Next
    INDEX
    Explanations

    rapidement, quickly

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

    synthetic identities, synthesized ecosystems

    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
    DLJ
    0.46
     虽然
    0.45
    (/
    0.45
     inital
    0.44
     съ
    0.43
    OPH
    0.43
    OMS
    0.43
     అమ
    0.42
    DSM
    0.42
    SIX
    0.42
    POSITIVE LOGITS
    嗚
    0.51
     cele
    0.47
    ᅪ
    0.46
    ische
    0.45
    聯盟
    0.43
     arid
    0.43
     Cele
    0.41
    不
    0.41
     terrib
    0.41
     rapidement
    0.41
    Activations Density 0.000%

    No Known Activations