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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7707
    Prev
    Next
    INDEX
    Explanations

    can, could, will

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

    open -

    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
    孖
    0.41
    primer
    0.40
    ฀
    0.38
     Vav
    0.38
    လျှ
    0.38
    aabb
    0.37
    ⌞
    0.37
     Improper
    0.36
    KeyboardView
    0.36
    ⃙
    0.36
    POSITIVE LOGITS
     tin
    0.53
     would
    0.51
     volition
    0.51
     can
    0.50
     could
    0.50
     might
    0.48
     does
    0.47
     should
    0.46
     will
    0.46
     μπο
    0.45
    Activations Density 0.209%

    No Known Activations