© 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. 4202
    Prev
    Next
    INDEX
    Explanations

    names after "and"

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

    names and titles in lists

    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
     मनुष्य
    0.21
     যুক্তরাষ্ট্রের
    0.21
    烺
    0.20
     სახელმწიფ
    0.20
     Linkedin
    0.20
    世界上最大的
    0.20
     భారతదేశ
    0.19
     بارے
    0.19
     वाणिज्य
    0.19
     foodservice
    0.19
    POSITIVE LOGITS
     Alex
    0.17
     zelfs
    0.16
    ጩ
    0.16
    Alex
    0.15
     навіть
    0.15
     nove
    0.14
     chased
    0.14
     elect
    0.14
     Jasmine
    0.14
     gasp
    0.14
    Activations Density 0.596%

    No Known Activations