© 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-65K
    7. 30782
    Prev
    Next
    INDEX
    Explanations

    Gentle softness

    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_65k_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
    潜在
    0.42
    晠
    0.39
     மொத்த
    0.39
    iprofloxacin
    0.37
    arschijnlijk
    0.37
     మాత్రమే
    0.37
    வதற்கான
    0.37
     устойчи
    0.36
    romagnet
    0.36
    ड़ने
    0.36
    POSITIVE LOGITS
     memo
    0.39
     sings
    0.39
     ز
    0.37
     heißt
    0.37
     womb
    0.37
     testifies
    0.37
     steht
    0.36
     soundtrack
    0.36
     ψ
    0.36
     ਯ
    0.36
    Activations Density 0.024%

    No Known Activations