© 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. 15524
    Prev
    Next
    INDEX
    Explanations

    topic headings and descriptions

    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
     revisit
    0.43
     Denis
    0.41
     D
    0.40
     Mut
    0.38
     DA
    0.38
     Eco
    0.38
     relatório
    0.38
     empir
    0.37
     viste
    0.37
     Robin
    0.37
    POSITIVE LOGITS
    5
    0.50
    );}
    0.45
    aknya
    0.45
    default
    0.45
    3
    0.45
     الأولى
    0.44
    cab
    0.43
    starttime
    0.43
    7
    0.42
    avaju
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.