© 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. 181280
    Prev
    Next
    INDEX
    Explanations

    different family, expand into

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

    hidden specific niches

    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
     immobile
    0.52
     immobili
    0.50
     alcalde
    0.48
     رئيس
    0.47
     />}></
    0.47
     बच्चे
    0.46
     प्रधान
    0.46
     hydroxide
    0.46
    िक्की
    0.46
     biodiesel
    0.46
    POSITIVE LOGITS
    ных
    0.52
    च्या
    0.52
    не
    0.52
     Proses
    0.50
    keits
    0.49
    게
    0.46
    다는
    0.45
    과
    0.45
     charlas
    0.45
     darf
    0.45
    Activations Density 0.001%

    No Known Activations