© 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. 59314
    Prev
    Next
    INDEX
    Explanations

    specific entities and their continuations

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

    hinted "could be"

    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
     Leistungs
    0.44
    素质
    0.38
     Vermö
    0.38
     vulnerability
    0.37
     disconnected
    0.37
    蕉
    0.37
     strongest
    0.37
     recurrent
    0.37
     haszn
    0.37
     sheaf
    0.37
    POSITIVE LOGITS
     поса
    0.50
     बाइ
    0.46
     Cushing
    0.45
    ซิตี
    0.45
    bart
    0.45
    ourse
    0.43
    cione
    0.43
     ентите
    0.43
    orium
    0.43
    𐰺
    0.43
    Activations Density 0.000%

    No Known Activations