© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 67391
    Prev
    Next
    INDEX
    Explanations

    cursor descriptions

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

    classifications 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
    艨
    0.54
     sodio
    0.52
     випад
    0.52
    στή
    0.52
    трі
    0.51
    avaju
    0.51
     prodotti
    0.51
    Jeśli
    0.50
    isol
    0.49
    蒹
    0.49
    POSITIVE LOGITS
     I
    0.44
     Where
    0.43
    衢
    0.43
     ":
    0.43
     Conservative
    0.43
     Institutions
    0.43
     Attribute
    0.42
     Complex
    0.42
     Flash
    0.41
     Greeting
    0.41
    Activations Density 0.001%

    No Known Activations