© 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. 246105
    Prev
    Next
    INDEX
    Explanations

    block chain, quality, attaching

    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
    菒
    0.50
    struktur
    0.49
    rektor
    0.49
    在这个
    0.48
    ಿಸುತ್ತ
    0.47
    َال
    0.47
    тат
    0.46
    在這個
    0.45
     Repeated
    0.45
    Moment
    0.44
    POSITIVE LOGITS
     motorsport
    0.46
     dupatta
    0.46
    ↵
    0.45
     หาก
    0.44
     proximity
    0.44
     уй
    0.44
     каче
    0.43
     motorcycl
    0.43
     таки
    0.43
     реги
    0.42
    Activations Density 0.000%

    No Known Activations