© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 23400
    Prev
    Next
    INDEX
    Explanations

    arrow keys

    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_40_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
     florals
    0.45
     ketiga
    0.44
     wreaths
    0.42
     palaces
    0.41
     countertops
    0.41
     꽃
    0.40
     flowers
    0.40
     fleurs
    0.39
    Gravestone
    0.39
    瑆
    0.39
    POSITIVE LOGITS
     arrow
    1.30
    arrow
    1.24
    Arrow
    1.22
     Arrow
    1.16
     arrows
    1.14
     Arrows
    1.11
    Arrows
    1.03
    箭头
    1.03
    arrows
    0.99
    ARROW
    0.93
    Activations Density 0.014%

    No Known Activations