© 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. 19587
    Prev
    Next
    INDEX
    Explanations

    Dennis Jaffe, After stage

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

    article prompts

    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
     realizzazione
    0.41
    预测
    0.39
    预
    0.39
    opt
    0.38
     ჰ
    0.38
    predicted
    0.38
     এদিন
    0.38
    াপনের
    0.38
     কোনো
    0.38
    𝓟
    0.38
    POSITIVE LOGITS
     motiv
    0.43
     levers
    0.42
     acceler
    0.40
     brazen
    0.40
     accél
    0.38
     McKay
    0.38
     Lana
    0.38
    ancia
    0.38
    쌔
    0.38
     bow
    0.37
    Activations Density 0.005%

    No Known Activations