© 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-262K
    7. 201261
    Prev
    Next
    INDEX
    Explanations

    describing actions, services, or interventions

    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
     clone
    0.54
     Route
    0.53
     TER
    0.51
     setValue
    0.49
     endocrine
    0.49
     biosynthetic
    0.47
     "
    0.47
     pituitary
    0.46
     high
    0.46
     HPLC
    0.46
    POSITIVE LOGITS
    Pray
    0.52
    lawful
    0.49
    materials
    0.48
    谗
    0.47
    лася
    0.47
    при
    0.47
    лах
    0.46
    падает
    0.46
    listed
    0.46
    лица
    0.46
    Activations Density 0.004%

    No Known Activations