© 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. 122011
    Prev
    Next
    INDEX
    Explanations

    announce something that

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

    processes, types, functions

    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
     Cheetah
    0.50
     dekor
    0.46
     decor
    0.45
    飾
    0.45
     Eski
    0.44
     intimid
    0.43
     overturned
    0.42
     expiresIn
    0.42
     metallurgy
    0.42
    邏
    0.42
    POSITIVE LOGITS
    ang
    0.46
    uster
    0.45
    um
    0.45
     কেন্দ্রের
    0.44
    ường
    0.43
    거
    0.43
    oster
    0.43
    brake
    0.43
    오
    0.43
    uerpo
    0.43
    Activations Density 0.000%

    No Known Activations