© 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. 242008
    Prev
    Next
    INDEX
    Explanations

    roles and actions

    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
    style
    0.50
    S
    0.48
    navbar
    0.46
    L
    0.46
    С
    0.45
    styles
    0.44
    tennis
    0.44
    stile
    0.44
     fouled
    0.44
    Tennis
    0.44
    POSITIVE LOGITS
     kosm
    0.50
     『
    0.48
    ṯ
    0.47
     Europa
    0.46
    ņa
    0.46
     crores
    0.45
    abhavena
    0.45
    hn
    0.45
     COMEN
    0.44
    ña
    0.43
    Activations Density 0.001%

    No Known Activations