© 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. 175203
    Prev
    Next
    INDEX
    Explanations

    classic travel

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

    marketing automation

    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
    and
    0.53
    with
    0.52
    will
    0.51
    title
    0.47
    were
    0.47
    วย
    0.47
    question
    0.47
    l
    0.47
    to
    0.46
    deal
    0.46
    POSITIVE LOGITS
     thái
    0.50
     dominant
    0.48
     Meier
    0.46
    _/
    0.46
     نیٹ
    0.46
     পাচ্ছি
    0.45
     CSM
    0.45
     ProductCategory
    0.45
    HttpRequest
    0.45
     quasi
    0.44
    Activations Density 0.000%

    No Known Activations