© 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. 155241
    Prev
    Next
    INDEX
    Explanations

    payments, or categories

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

    compelled against

    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
     međ
    0.47
     membuatnya
    0.45
    িতি
    0.44
     February
    0.44
    ர்வு
    0.43
    きの
    0.43
     তারাও
    0.43
    키
    0.43
     zaken
    0.41
     Vanden
    0.41
    POSITIVE LOGITS
    adir
    0.57
    kable
    0.52
    ’
    0.52
    Memento
    0.51
    Encom
    0.49
    agré
    0.48
     vassals
    0.48
    st
    0.47
    vase
    0.47
     desempe
    0.46
    Activations Density 0.000%

    No Known Activations