© 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. 198163
    Prev
    Next
    INDEX
    Explanations

    morning, margins, identity, Palm

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

    inherits, into, outcome, classic

    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
     investors
    0.52
    ​
    0.47
     OnePlus
    0.46
     Xiaomi
    0.45
    ↵↵
    0.45
     launched
    0.44
     electromagnetic
    0.43
     UConn
    0.43
     biotech
    0.43
     recruits
    0.43
    POSITIVE LOGITS
    愆
    0.53
    док
    0.50
    挲
    0.48
    悳
    0.48
    谬
    0.48
    楇
    0.48
    慜
    0.47
    笞
    0.47
    Prothorax
    0.46
    тері
    0.46
    Activations Density 0.003%

    No Known Activations