© 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. 83955
    Prev
    Next
    INDEX
    Explanations

    shady land, Nixon Shock, ties that

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

    He first following ambled shuffled

    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
     Mail
    0.55
     k
    0.52
     Z
    0.52
     Augusta
    0.50
     IFC
    0.49
     Influence
    0.49
     ISP
    0.49
     Eclipse
    0.49
     Entrepreneur
    0.48
     Internet
    0.48
    POSITIVE LOGITS
    etermined
    0.50
    ת
    0.49
    áte
    0.49
    Kaynak
    0.47
    Skippable
    0.47
    церт
    0.47
     détermine
    0.47
    τή
    0.47
    NOWLED
    0.47
    нти
    0.46
    Activations Density 0.001%

    No Known Activations