© 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. 194246
    Prev
    Next
    INDEX
    Explanations

    authors and topics

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

    Beginners creating sales techniques

    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
     катастро
    0.42
    гри
    0.41
    нев
    0.41
    ѐ
    0.38
    ин
    0.38
    എസ്
    0.38
    сь
    0.37
     Пред
    0.36
    عرِّف
    0.36
    СТЕ
    0.36
    POSITIVE LOGITS
    princess
    0.48
     bliss
    0.46
     laziness
    0.46
    ！！！
    0.45
     princess
    0.44
     shayari
    0.44
     minimalistic
    0.44
     salwar
    0.43
    ！
    0.43
     upto
    0.43
    Activations Density 0.000%

    No Known Activations