© 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. 251867
    Prev
    Next
    INDEX
    Explanations

    Display market, lymph node, physical address, small groups

    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
     Using
    0.47
     무
    0.42
     চায়
    0.41
     Though
    0.41
     Replacing
    0.40
    jeux
    0.40
     hứng
    0.40
     использует
    0.39
     버전
    0.39
     submarines
    0.38
    POSITIVE LOGITS
     hospitalization
    0.51
     pamoja
    0.49
     imaged
    0.46
     hospitalized
    0.45
    味わ
    0.45
    +(
    0.45
     pasien
    0.44
     आली
    0.41
     symbolically
    0.41
    beeld
    0.41
    Activations Density 0.001%

    No Known Activations