© 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. 34547
    Prev
    Next
    INDEX
    Explanations

    invest and trade

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

    streaming video architecture

    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
     couvertures
    0.50
    食べた
    0.49
    闡
    0.47
    ки
    0.45
    بك
    0.45
     regl
    0.45
    नगर
    0.45
     alcal
    0.44
    بالإنجليزية
    0.44
     opi
    0.44
    POSITIVE LOGITS
    为主
    0.44
    shad
    0.43
    Iniciar
    0.41
    was
    0.40
     highlighted
    0.40
     horrific
    0.40
    Steven
    0.39
    Bois
    0.39
    唰
    0.38
     obviamente
    0.38
    Activations Density 0.001%

    No Known Activations