© 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. 181583
    Prev
    Next
    INDEX
    Explanations

    trip to

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

    medical, benign, chambers, flow, Leo, CX

    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
     σαν
    0.53
     Еў
    0.52
    ጇ
    0.49
     農
    0.47
     nhà
    0.44
     電
    0.44
    ோது
    0.44
     dó
    0.44
     νό
    0.44
     muertos
    0.44
    POSITIVE LOGITS
    та
    0.62
    ia
    0.48
     Generalized
    0.47
    ↵↵
    0.46
    al
    0.46
    Generalized
    0.44
    ו
    0.43
    סט
    0.43
    Access
    0.42
    adder
    0.42
    Activations Density 0.001%

    No Known Activations