© 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. 121138
    Prev
    Next
    INDEX
    Explanations

    vs

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

    who or what

    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
    us
    0.55
    z
    0.52
    陷入
    0.47
    ant
    0.46
    alea
    0.45
    rescences
    0.45
     permangan
    0.45
    冗
    0.44
    alg
    0.44
     deformations
    0.43
    POSITIVE LOGITS
     সমী
    0.46
    Paying
    0.46
    🇮
    0.45
    閪
    0.44
    ഷ്‌
    0.44
    𝕖
    0.43
    Played
    0.42
    ᚕ
    0.42
    㑹
    0.41
     ज़्यादा
    0.41
    Activations Density 0.001%

    No Known Activations