© 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. 96369
    Prev
    Next
    INDEX
    Explanations

    spending details and outcomes

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

    original content or projects

    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
     %),
    0.45
     \%
    0.44
     excitatory
    0.43
    produced
    0.42
     Jdbc
    0.42
     compuls
    0.42
     synerg
    0.42
     '/
    0.41
     Projected
    0.41
    stimulated
    0.41
    POSITIVE LOGITS
    里克
    0.47
    городе
    0.46
    好看
    0.46
    东南
    0.46
    原始内容存档于
    0.46
     recovering
    0.45
    本作
    0.44
    }']
    0.44
    Lo
    0.44
    原创
    0.43
    Activations Density 0.001%

    No Known Activations