© 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. 179060
    Prev
    Next
    INDEX
    Explanations

    plurality vote

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

    body and physical sensations

    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
    lere
    0.52
    O
    0.50
    lari
    0.48
    lores
    0.48
    kinase
    0.48
     FabD
    0.48
    வ
    0.47
    lare
    0.47
    eday
    0.47
    ಮಾ
    0.47
    POSITIVE LOGITS
    拍
    0.44
    上的
    0.42
    齁
    0.42
    就在
    0.42
     míst
    0.42
    不断
    0.41
    扣
    0.41
    <td>
    0.40
    闸
    0.40
    ሪ
    0.40
    Activations Density 0.000%

    No Known Activations