© 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. 26221
    Prev
    Next
    INDEX
    Explanations

    articles followed by descriptive nouns

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

    negative context and specific outcomes

    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
    ArchiveAction
    0.51
    联动
    0.50
    offre
    0.50
    Citizen
    0.47
    Kinds
    0.47
    能够
    0.46
    람
    0.46
    ądź
    0.46
    فانه
    0.46
    zan
    0.45
    POSITIVE LOGITS
     ۹
    0.46
     دیا۔
    0.45
     دی
    0.45
     ferrite
    0.45
     strontium
    0.45
     missile
    0.45
     ethylene
    0.43
     cesium
    0.43
     missiles
    0.43
     newline
    0.43
    Activations Density 0.000%

    No Known Activations