© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 29287
    Prev
    Next
    INDEX
    Explanations

    health policies, former Venezuelan

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

    tumblers, casual relationships, orchestration

    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
    一定是
    0.49
    GYPT
    0.46
    ন
    0.46
    耑
    0.45
         
    0.45
    URATION
    0.45
    =:
    0.44
    lijah
    0.44
    毯
    0.44
    相关
    0.44
    POSITIVE LOGITS
     inconsistency
    0.53
     SWOT
    0.52
    များနှင့်
    0.51
     Flushing
    0.51
     monitoring
    0.47
    די
    0.47
     critique
    0.47
     evaluation
    0.47
     parametrization
    0.47
     aspiring
    0.46
    Activations Density 0.000%

    No Known Activations