© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1626
    Prev
    Next
    INDEX
    Explanations

    you will be

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

    transforms words

    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_53_width_65k_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
    ఆ
    0.36
    ಳಿತ
    0.35
    㓦
    0.34
     божомолдор
    0.33
    𐰆
    0.33
     personenbez
    0.32
     LOTRAchievement
    0.32
     muu
    0.32
    𝗠
    0.32
     givenChar
    0.32
    POSITIVE LOGITS
     discover
    0.46
     possibly
    0.46
    possibly
    0.42
     undoubtedly
    0.41
     possess
    0.40
     obtain
    0.39
     aren
    0.39
     have
    0.39
     permit
    0.38
     merely
    0.37
    Activations Density 0.689%

    No Known Activations