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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 36767
    Prev
    Next
    INDEX
    Explanations

    personal preference or exclusivity

    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
    table
    0.45
    RxDocument
    0.44
    <!--
    0.44
    possessed
    0.43
    コツ
    0.43
     рецеп
    0.41
     '?
    0.40
    title
    0.40
    <?
    0.40
    血管
    0.40
    POSITIVE LOGITS
     Verständnis
    0.52
     to
    0.46
     Deux
    0.45
     केवल
    0.44
     préférence
    0.43
     solamente
    0.43
     sendiri
    0.42
    amente
    0.42
     seulement
    0.42
     personalmente
    0.42
    Activations Density 0.001%

    No Known Activations