© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 50232
    Prev
    Next
    INDEX
    Explanations

    Decentral, name, DSP, separates

    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_65k_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
     vacate
    0.50
     piena
    0.48
    ᱢ
    0.47
    ਸ਼
    0.47
    TL
    0.46
    आरपी
    0.45
     llena
    0.45
    Š
    0.45
     fluvial
    0.45
     kuri
    0.44
    POSITIVE LOGITS
    كر
    0.46
    ²+
    0.43
    ى
    0.43
     تاز
    0.42
    铂
    0.41
    بال
    0.40
     بالك
    0.40
     اكتوبر
    0.40
    bitro
    0.40
    號
    0.40
    Activations Density 0.029%

    No Known Activations