© 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. 20163
    Prev
    Next
    INDEX
    Explanations

    URLs and web addresses

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

    d attribute or key-value pairs

    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
    Ｃ
    0.49
    library
    0.47
    preview
    0.46
     Library
    0.46
    PRO
    0.45
    PRE
    0.45
    resolve
    0.45
    section
    0.45
    Web
    0.45
    ="
    0.45
    POSITIVE LOGITS
    StillWater
    0.52
     pastors
    0.51
     diarrhoea
    0.50
     weir
    0.49
     weaning
    0.49
     sepd
    0.49
     sebum
    0.48
     lavage
    0.48
     barbit
    0.48
     mayonnaise
    0.47
    Activations Density 0.000%

    No Known Activations