© 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. 73221
    Prev
    Next
    INDEX
    Explanations

    family members

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

    first over the horizon/swimming

    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
    :
    0.47
     Maple
    0.47
     Cooler
    0.46
     (,
    0.46
     &
    0.46
     pH
    0.46
     Query
    0.44
     Цвет
    0.44
     Cement
    0.42
     Shader
    0.41
    POSITIVE LOGITS
    কর্ণ
    0.49
     employé
    0.48
    ırd
    0.46
     utilizzato
    0.45
    राष्ट
    0.44
     oggetto
    0.44
     sportive
    0.44
    🐧
    0.44
    🛶
    0.44
     utilisé
    0.44
    Activations Density 0.000%

    No Known Activations