© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 221939
    Prev
    Next
    INDEX
    Explanations

    conversational continuations after refusals

    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_40_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
    愘
    0.43
    astica
    0.40
    erro
    0.40
     firmas
    0.38
    errors
    0.38
    Columbus
    0.37
     danno
    0.37
    ﺟ
    0.37
    㽚
    0.37
    lambda
    0.36
    POSITIVE LOGITS
     समर्थ
    0.42
     ಸಾಧ
    0.41
     बाद
    0.41
     після
    0.40
     आंदोल
    0.39
     เด่น
    0.39
     일어나
    0.38
     Avoid
    0.38
     ſt
    0.38
    ヒル
    0.38
    Activations Density 0.001%

    No Known Activations