© 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. 26711
    Prev
    Next
    INDEX
    Explanations

    advanced features and tools

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

    Boxer shorts, your mass

    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
     July
    0.46
    <code>
    0.44
     Kilometer
    0.43
    vi
    0.42
     Conversations
    0.41
     Mercer
    0.39
    軋
    0.39
     August
    0.39
    運転
    0.39
     Abstracts
    0.39
    POSITIVE LOGITS
     위하여
    0.53
     곱
    0.50
     photoshop
    0.46
    곱
    0.46
    捚
    0.45
     사용하여
    0.45
    挼
    0.45
     위해
    0.44
    糈
    0.44
    RefManager
    0.43
    Activations Density 0.000%

    No Known Activations