© 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. 122573
    Prev
    Next
    INDEX
    Explanations

    consumer

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

    quick start or tweaks

    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
    Millan
    0.47
     Пред
    0.46
    ችል
    0.46
     External
    0.46
    Control
    0.45
    巉
    0.45
    ष्कार
    0.45
    ন্স
    0.44
    elective
    0.44
    Пред
    0.44
    POSITIVE LOGITS
     konsumen
    0.47
    ,
    0.46
     consumer
    0.45
     গ্রাহ
    0.44
     chưa
    0.43
     gastron
    0.43
    ,"
    0.42
     ভোক্ত
    0.42
    ,”
    0.42
     consumidores
    0.42
    Activations Density 0.000%

    No Known Activations