© 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. 40-GEMMASCOPE-2-RES-262K
    7. 222742
    Prev
    Next
    INDEX
    Explanations

    estimating pi and similarity

    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_40_width_262k_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
    дца
    0.36
    കര
    0.35
     प्रकार
    0.35
     प्रस
    0.34
    月に
    0.32
     notation
    0.31
    노
    0.31
     indication
    0.31
    ertype
    0.31
    ADA
    0.31
    POSITIVE LOGITS
    widgetTo
    0.45
    "".
    0.44
    storageModule
    0.41
    myCollision
    0.40
     objString
    0.40
    alignParentRight
    0.39
    ச்சின்ன
    0.36
    '".
    0.36
    -​
    0.36
     Oed
    0.36
    Activations Density 0.078%

    No Known Activations