© 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. 121047
    Prev
    Next
    INDEX
    Explanations

    website again

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

    vulnerability, poverty, education, health

    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
    ية
    0.58
    ish
    0.51
    t
    0.51
    r
    0.50
    premi
    0.48
    ite
    0.46
    y
    0.46
    )_{
    0.46
    wing
    0.46
    ロ
    0.44
    POSITIVE LOGITS
    خدم
    0.46
     Стре
    0.45
     دوبارہ
    0.45
     TGC
    0.44
     servicio
    0.44
     zahlen
    0.44
    updateConfirm
    0.43
     دین
    0.43
     testimonials
    0.43
    madı
    0.42
    Activations Density 0.001%

    No Known Activations