© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 5172
    Prev
    Next
    INDEX
    Explanations

    email and personal narratives

    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
    Ĭ
    0.38
    <eos>
    0.38
    uli
    0.38
    ائب
    0.38
     toate
    0.37
    ube
    0.37
    oge
    0.37
    l
    0.36
     zodat
    0.35
    eles
    0.35
    POSITIVE LOGITS
    </blockquote>
    0.57
    ޏ
    0.50
     まま
    0.40
    Section
    0.39
     tasmim
    0.39
     TextInputLayout
    0.39
     rupam
    0.39
    */}
    0.39
    ...*/
    0.39
    ынша
    0.38
    Activations Density 0.022%

    No Known Activations