© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 150976
    Prev
    Next
    INDEX
    Explanations

    describing roles and relationships

    np_acts-logits-general · gemini-2.5-flash-lite

    finding quotes and parentheticals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EN
    0.54
    λα
    0.51
    ι
    0.50
     adimensional
    0.48
     optimize
    0.47
    ASE
    0.46
    EDA
    0.46
    з
    0.46
     ridurre
    0.46
    ύ
    0.45
    POSITIVE LOGITS
    elijke
    0.51
    钅
    0.48
     రచన
    0.47
     แน
    0.47
    ముఖ
    0.46
     ಹಿಂದೆ
    0.45
    fool
    0.45
     మాట్లాడు
    0.44
     একই
    0.44
    länd
    0.43
    Activations Density 0.000%

    No Known Activations