© 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. 6064
    Prev
    Next
    INDEX
    Explanations

    sentence starters and phrases

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

    World War

    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
     중에서
    0.43
     把
    0.39
    ᆢ
    0.38
    いろいろ
    0.37
     früheren
    0.37
     żeby
    0.36
     supaya
    0.36
     বেশির
    0.35
     snd
    0.35
     lekin
    0.35
    POSITIVE LOGITS
    へと
    0.45
     entirety
    0.42
    依旧
    0.42
     কার্যক্রম
    0.41
     সম্মুখে
    0.41
     துவ
    0.40
    為
    0.39
     únicamente
    0.38
     تمامی
    0.38
     Alongside
    0.38
    Activations Density 0.408%

    No Known Activations