© 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. 113109
    Prev
    Next
    INDEX
    Explanations

    another entry

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

    Analyzing features, krill, sinkholes

    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
     Ciencias
    0.50
     осві
    0.49
    冊
    0.48
    போ
    0.48
    대를
    0.48
     educativos
    0.46
    पी
    0.46
    釐
    0.46
    मंड
    0.46
     Macri
    0.46
    POSITIVE LOGITS
    f
    0.54
     h
    0.49
    0.46
    ili
    0.44
    iste
    0.44
     hi
    0.44
    urt
    0.43
     করিত
    0.43
    ipu
    0.43
    ex
    0.43
    Activations Density 0.001%

    No Known Activations