© 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. 23919
    Prev
    Next
    INDEX
    Explanations

    conditional offers and suggestions

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

    with condoms

    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
     priori
    0.44
     sol
    0.41
     piccolo
    0.39
    ならば
    0.39
     verv
    0.38
     ressort
    0.38
    )]
    0.38
    Facet
    0.38
    Locale
    0.37
    orld
    0.37
    POSITIVE LOGITS
     लिह
    0.43
     महत्त्वपूर्ण
    0.42
     جامعة
    0.39
    teddy
    0.38
     Tháng
    0.38
    +{
    0.38
    ágico
    0.38
     Mourinho
    0.37
    memberName
    0.37
    *****",
    0.37
    Activations Density 0.000%

    No Known Activations