© 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. 133352
    Prev
    Next
    INDEX
    Explanations

    payment and agreement terms

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

    involvement or consequence

    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
    ussians
    0.47
     Sees
    0.46
    専門
    0.44
     جاه
    0.43
    นู
    0.43
     মুগ্ধ
    0.42
    oires
    0.42
    🌐
    0.41
    𓈒
    0.41
    絶対に
    0.41
    POSITIVE LOGITS
     bakım
    0.46
     involuc
    0.45
     enfo
    0.45
     yearling
    0.45
     conformance
    0.45
     udział
    0.44
     إجراء
    0.44
     autofocus
    0.44
     enfoc
    0.44
     participa
    0.43
    Activations Density 0.000%

    No Known Activations