© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 84164
    Prev
    Next
    INDEX
    Explanations

    own fireworks, market share, business organization

    np_acts-logits-general · gemini-2.5-flash-lite

    sentence completion prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    膯
    0.55
     Υ
    0.55
    úncia
    0.54
    䏲
    0.53
    梼
    0.52
     Corolle
    0.51
    )【
    0.51
    URNIZOR
    0.50
     únic
    0.50
     Zugang
    0.49
    POSITIVE LOGITS
    ipton
    0.49
     jobb
    0.46
     jones
    0.45
     behaviors
    0.42
     noise
    0.42
     colleges
    0.42
     J
    0.41
     batteries
    0.41
     beach
    0.40
     raw
    0.40
    Activations Density 0.001%

    No Known Activations