© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199386
    Prev
    Next
    INDEX
    Explanations

    interviews, scale, cycle, personal, threats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    غيرة
    0.45
     Ignatius
    0.44
     دستور
    0.43
     الأرض
    0.43
    ّل
    0.43
    彘
    0.43
    كبر
    0.41
    inį
    0.41
     !}
    0.40
    𝒙
    0.40
    POSITIVE LOGITS
     bloke
    0.47
    起こ
    0.45
    r
    0.45
    cuk
    0.44
     baz
    0.43
     cama
    0.43
    ophys
    0.43
    ekin
    0.43
    体
    0.42
    ට
    0.42
    Activations Density 0.002%

    No Known Activations