© 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. 6063
    Prev
    Next
    INDEX
    Explanations

    manager, guidelines, tendencies, aesthetic, alternatives, phenomenal

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

    general knowledge and

    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
     antibodies
    0.33
     M
    0.31
     C
    0.31
     four
    0.30
     six
    0.30
     three
    0.30
     B
    0.29
     drei
    0.29
     AGN
    0.29
     two
    0.28
    POSITIVE LOGITS
    🤑
    0.33
    Droite
    0.33
    Vale
    0.32
    Vecchio
    0.30
    Lorsque
    0.30
    ља
    0.30
    Flair
    0.30
    Tecla
    0.29
    💹
    0.29
    🕍
    0.29
    Activations Density 1.502%

    No Known Activations