© 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. 142210
    Prev
    Next
    INDEX
    Explanations

    native to the platform

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

    budget and sentiment

    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
    리오
    0.58
    鹫
    0.57
    ٰی
    0.56
    되었
    0.50
    یکس
    0.50
    人気の
    0.49
     regione
    0.49
     całym
    0.49
    pValue
    0.48
    ایج
    0.48
    POSITIVE LOGITS
    I
    0.44
     I
    0.44
    Creat
    0.41
     collaborators
    0.41
    aporte
    0.41
    oll
    0.40
     Very
    0.40
    u
    0.39
    at
    0.39
     nast
    0.38
    Activations Density 0.001%

    No Known Activations