© 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. 44945
    Prev
    Next
    INDEX
    Explanations

    painting, returns, data, questions

    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
     linea
    0.44
     stay
    0.43
     स्
    0.43
     smile
    0.41
     삶
    0.41
     casing
    0.39
     desag
    0.39
     unwelcome
    0.39
     keep
    0.39
     BAM
    0.39
    POSITIVE LOGITS
    োজন
    0.44
    ftest
    0.39
    崞
    0.39
    ]।
    0.38
    nitz
    0.37
    payer
    0.36
     vardı
    0.36
    аст
    0.36
    事前に
    0.36
    oinen
    0.36
    Activations Density 0.008%

    No Known Activations