© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14915
    Prev
    Next
    INDEX
    Explanations

    actions, services, and states

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

    long-tail keywords

    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_16k_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
     древ
    0.55
     două
    0.52
    ـ
    0.49
    الأ
    0.48
     દવા
    0.48
    RI
    0.47
    French
    0.46
    ă
    0.46
    Ancient
    0.46
     الكت
    0.45
    POSITIVE LOGITS
     reasoned
    0.48
    ).
    0.42
     Änderung
    0.42
     parameter
    0.41
     persuade
    0.41
    DisplayStyle
    0.40
    permission
    0.40
    timestamp
    0.40
    }=
    0.39
     plausible
    0.39
    Activations Density 0.001%

    No Known Activations