© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29393
    Prev
    Next
    INDEX
    Explanations

    all or each distribution

    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
     내용
    0.43
     împre
    0.41
     mnoh
    0.40
     مانند
    0.39
     ಮಾಹಿತಿ
    0.38
     مار
    0.38
    浯
    0.38
     walaupun
    0.37
    많
    0.37
    <unused1999>
    0.37
    POSITIVE LOGITS
     each
    0.54
     all
    0.45
     ANY
    0.45
     different
    0.42
    ÜR
    0.42
     various
    0.41
     olika
    0.41
     ALL
    0.40
    କୁ
    0.39
     soils
    0.39
    Activations Density 0.098%

    No Known Activations