© 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. 128016
    Prev
    Next
    INDEX
    Explanations

    plan on, Series Squadron

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

    explain complex information

    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
    !
    0.47
     acerca
    0.46
     عفوا
    0.45
     resisted
    0.43
     uns
    0.43
     robbed
    0.43
     imparted
    0.43
     scrolled
    0.42
     iterations
    0.42
     alma
    0.42
    POSITIVE LOGITS
    ᖓ
    0.53
    𝓻
    0.52
    𝐃
    0.52
    𝓭
    0.52
    蒎
    0.52
     बँके
    0.51
    ਡ
    0.51
    疫情防控
    0.49
    ড
    0.49
     segmento
    0.49
    Activations Density 0.001%

    No Known Activations