© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23428
    Prev
    Next
    INDEX
    Explanations

    ratios and calculations

    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_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
    爾
    0.48
    intArray
    0.47
    ៣
    0.46
    ˧
    0.46
    ო
    0.45
    𝟰
    0.45
    संस्करण
    0.45
    ३
    0.43
    vrdr
    0.43
    𝕡
    0.42
    POSITIVE LOGITS
    0.50
    ’
    0.45
     suspect
    0.45
     cease
    0.44
     fulfill
    0.43
     guardar
    0.43
     telles
    0.42
     ie
    0.42
     canc
    0.41
     ceased
    0.41
    Activations Density 0.002%

    No Known Activations