© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10105
    Prev
    Next
    INDEX
    Explanations

    producing outputs

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

    production or output

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

    produced

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
     Modular
    0.41
    ceptors
    0.41
    მის
    0.38
    흡
    0.37
    頰
    0.37
    柳
    0.37
    旯
    0.37
     capacités
    0.36
     AgNO
    0.36
     рецеп
    0.36
    POSITIVE LOGITS
     produced
    1.07
     formed
    0.99
     Produced
    0.98
    produced
    0.95
     produit
    0.90
    产生的
    0.90
     terbentuk
    0.90
     produ
    0.89
     produziert
    0.88
     producido
    0.88
    Activations Density 0.328%

    No Known Activations