© 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. 649
    Prev
    Next
    INDEX
    Explanations

    annual report

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

    compound noun phrases

    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
    <unused497>
    0.49
    ın
    0.49
    ní
    0.49
    ۷
    0.48
    8
    0.47
     দ্বিতীয়
    0.46
    6
    0.46
    та
    0.45
     başlad
    0.45
    dır
    0.45
    POSITIVE LOGITS
    💒
    0.38
     condos
    0.38
     porches
    0.36
    不断的
    0.36
    !!!!
    0.35
    Ibid
    0.35
    🤨
    0.34
    比如
    0.34
    !!!"
    0.34
    !!!
    0.34
    Activations Density 0.467%

    No Known Activations