© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7964
    Prev
    Next
    INDEX
    Explanations

    balloons and floating objects

    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_16k_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
     woodpe
    0.44
    विचार
    0.42
    घ
    0.42
     hydraulic
    0.41
    砍
    0.40
    锹
    0.40
    Direct
    0.39
    ধান
    0.39
     blacksmith
    0.39
    гих
    0.39
    POSITIVE LOGITS
     balloons
    0.95
     Balloons
    0.88
     balloon
    0.81
     floating
    0.80
    🎈
    0.79
     Balloon
    0.76
     floated
    0.76
     Floating
    0.73
    Balloon
    0.72
    floating
    0.71
    Activations Density 0.209%

    No Known Activations