© 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. 136836
    Prev
    Next
    INDEX
    Explanations

    medical, financial, technical contexts

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

    Lifestyle Factors

    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
    Half
    0.56
    5
    0.56
    虚
    0.53
    Сер
    0.50
    half
    0.49
    MIC
    0.48
    8
    0.48
    6
    0.48
    Dz
    0.47
    use
    0.47
    POSITIVE LOGITS
     dėl
    0.52
    ijama
    0.46
    ectoria
    0.45
     storica
    0.45
    瞔
    0.45
     aguda
    0.44
     (),
    0.44
     valut
    0.43
     或者
    0.43
     '',
    0.43
    Activations Density 0.000%

    No Known Activations