© 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. 128489
    Prev
    Next
    INDEX
    Explanations

    surrounding, product, loan, car, buy

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

    identification, encoding, format, outfits

    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
     بسته
    0.49
    orithm
    0.45
     واپ
    0.44
    reducing
    0.44
    ቝ
    0.44
    にした
    0.42
     legislation
    0.41
     போல்
    0.41
     کاهش
    0.41
     سپاه
    0.41
    POSITIVE LOGITS
     trycatch
    0.50
     runnable
    0.46
     нужно
    0.43
     ExifInterface
    0.42
    <?,
    0.42
     habitually
    0.42
    假日
    0.41
    ར་
    0.41
     purposefully
    0.40
     मुस्कुरा
    0.40
    Activations Density 0.002%

    No Known Activations