© 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. 99720
    Prev
    Next
    INDEX
    Explanations

    foreign languages and specific words

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

    eclipses, topics, DHCP server

    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
    模式
    0.42
    )$
    0.41
    比如
    0.41
    άζ
    0.40
    Volatility
    0.38
    =-\
    0.37
     excitations
    0.37
     synapses
    0.37
    薄
    0.37
     घन
    0.37
    POSITIVE LOGITS
     Sankt
    0.43
     Геор
    0.43
     Warum
    0.43
     ternyata
    0.42
    老爷
    0.42
     swojego
    0.41
     feng
    0.40
     semplic
    0.40
    ström
    0.40
     conflicto
    0.40
    Activations Density 0.003%

    No Known Activations