© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9836
    Prev
    Next
    INDEX
    Explanations

    company names and associated actions

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

    names like Sonny, James, Bjarnason, Heung-min

    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_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
    доста
    0.43
    ств
    0.40
     फ
    0.37
    शय
    0.37
    städ
    0.37
    論文
    0.36
    主的
    0.35
     fundamentos
    0.35
     Cuts
    0.35
    函数
    0.33
    POSITIVE LOGITS
     magnific
    0.40
     hoi
    0.39
     dunno
    0.39
    </h4>
    0.38
    nEnter
    0.38
    égi
    0.36
     PON
    0.36
     //!
    0.36
    갬
    0.36
     con
    0.35
    Activations Density 0.322%

    No Known Activations