Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 18840
    Prev
    Next
    INDEX
    Explanations

    valuable insights or unwanted sexual content

    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
    式の
    0.57
    වාස
    0.52
    _
    0.49
    rzez
    0.49
    FBSDKLogin
    0.48
    (
    0.48
     violators
    0.47
    that
    0.47
     būti
    0.47
     निर्धारण
    0.47
    POSITIVE LOGITS
     hilfre
    0.60
     hilfreich
    0.60
    ла
    0.59
     Informationen
    0.57
     in
    0.56
     useful
    0.56
     informasjon
    0.54
    ล
    0.52
     ferramenta
    0.51
     herramienta
    0.50
    Activations Density 0.052%

    No Known Activations