© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 53232
    Prev
    Next
    INDEX
    Explanations

    already known

    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
    ini
    0.46
    init
    0.45
    下さい
    0.44
     capucha
    0.43
     cashew
    0.43
    >',
    0.42
     clinically
    0.41
    broke
    0.41
     exibir
    0.41
    até
    0.39
    POSITIVE LOGITS
     Haft
    0.47
     SWOT
    0.45
     Passe
    0.44
    燧
    0.43
     Skor
    0.43
     Transmission
    0.42
     Auswahl
    0.41
     Vulner
    0.41
     Suicide
    0.40
     Schwarzen
    0.40
    Activations Density 0.018%

    No Known Activations