© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 167492
    Prev
    Next
    INDEX
    Explanations

    javascript variable declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aren
    0.39
     go
    0.38
     await
    0.38
     커
    0.37
     assemble
    0.37
     assemblies
    0.36
    Won
    0.36
    ựng
    0.36
     girlfriend
    0.35
    ZZ
    0.35
    POSITIVE LOGITS
    送
    0.45
    فن
    0.42
    возмо
    0.41
     தொடர்பாக
    0.40
    ക്കുറിച്ച്
    0.40
     ಪ್ರಶ್
    0.40
    気温
    0.40
     sak
    0.39
    ਗੀ
    0.39
    ňuje
    0.39
    Activations Density 0.001%

    No Known Activations