© 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. 16-GEMMASCOPE-2-RES-262K
    7. 119675
    Prev
    Next
    INDEX
    Explanations

    hostnames and network names

    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_16_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
    ̀ng
    0.66
     méthodes
    0.64
    ための
    0.63
     recettes
    0.62
     misused
    0.61
     lesión
    0.60
     براي
    0.60
    ୍
    0.59
    因為
    0.58
     акчага
    0.57
    POSITIVE LOGITS
    la
    0.67
    te
    0.67
     AC
    0.63
     Oh
    0.60
     ACH
    0.60
     ANOVA
    0.60
     Vero
    0.60
     V
    0.57
    bl
    0.57
     ATO
    0.57
    Activations Density 0.002%

    No Known Activations