© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53816
    Prev
    Next
    INDEX
    Explanations

    explanation of items starting with "2. "

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FBSDKInternal
    0.51
     (“
    0.50
     მიმოწერა
    0.48
    ).\\
    0.46
    politik
    0.45
     Kähler
    0.44
    ꞌ
    0.44
     xhrObj
    0.44
    tsprec
    0.43
    chacha
    0.43
    POSITIVE LOGITS
    ल
    0.66
    accurate
    0.56
    र
    0.50
    oll
    0.50
    olon
    0.49
    Series
    0.49
    Award
    0.49
    Га
    0.49
    ंखला
    0.48
    showing
    0.48
    Activations Density 0.009%

    No Known Activations