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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 7423
    Prev
    Next
    INDEX
    Explanations

    medical conditions and personal data

    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
     کمار
    0.45
    emir
    0.45
     releasing
    0.45
    釋
    0.43
     universality
    0.42
    夎
    0.42
     summand
    0.41
     داده
    0.40
     satta
    0.40
     regard
    0.40
    POSITIVE LOGITS
    </em>
    0.55
     但是
    0.47
    umbles
    0.44
     первый
    0.44
    ба
    0.44
    </strong>
    0.44
     बातचीत
    0.44
    வாங்க
    0.43
    лу
    0.43
    characterized
    0.43
    Activations Density 0.011%

    No Known Activations