© 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. 184497
    Prev
    Next
    INDEX
    Explanations

    Angola and Angolan President

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

    common phrases and lists

    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
    Did
    0.46
    퇴
    0.45
    is
    0.45
    shorts
    0.45
    mid
    0.44
    urbs
    0.44
    <h1>
    0.43
    료
    0.43
    держа
    0.43
    springboot
    0.42
    POSITIVE LOGITS
     favorable
    0.52
     selen
    0.51
     metast
    0.49
     coag
    0.49
     metastable
    0.48
     functionally
    0.48
     sculpted
    0.48
     fluor
    0.48
     coagulation
    0.47
     halos
    0.46
    Activations Density 0.001%

    No Known Activations