© 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. 52079
    Prev
    Next
    INDEX
    Explanations

    during another activity

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

    waiting for actions or responses

    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
    均匀
    0.44
     eastward
    0.44
    ,":
    0.44
     westward
    0.44
     சிறிது
    0.42
    絃
    0.41
     четыре
    0.40
    躍
    0.39
    二十
    0.38
    ５
    0.38
    POSITIVE LOGITS
     Billing
    0.46
     واقعات
    0.44
     сути
    0.43
     rồi
    0.43
     Emergency
    0.43
     Banking
    0.42
     same
    0.41
     samme
    0.40
     Casualty
    0.40
     gleichen
    0.40
    Activations Density 0.000%

    No Known Activations