© 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. 179021
    Prev
    Next
    INDEX
    Explanations

    first few, typical american, customer needs

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

    especially during, would 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
    缺
    0.50
     Vì
    0.44
     ^=
    0.44
    %
    0.43
    난
    0.43
     QR
    0.42
    CRED
    0.42
    ^
    0.42
     জ্বর
    0.42
    E
    0.41
    POSITIVE LOGITS
    ულის
    0.53
    ელის
    0.49
     extremities
    0.46
    UMBIA
    0.45
     underlines
    0.45
     اُ
    0.44
    putted
    0.44
    ುತ್ತಾರೆ
    0.44
    統領
    0.44
     patří
    0.44
    Activations Density 0.002%

    No Known Activations