© 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. 135238
    Prev
    Next
    INDEX
    Explanations

    businesswritersGem

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

    ongoing humanitarian concerns

    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
    ార్లు
    0.57
     різні
    0.49
     відповіда
    0.48
    詑
    0.47
    BURSEMENTS
    0.47
     compagnie
    0.46
     Turquoise
    0.45
    ⚈
    0.45
     %@",
    0.45
    উল্লেখ্য
    0.45
    POSITIVE LOGITS
    up
    0.65
    on
    0.64
    v
    0.63
    wa
    0.55
    isa
    0.55
    ya
    0.54
    un
    0.52
    zu
    0.52
    pn
    0.51
    s
    0.51
    Activations Density 0.001%

    No Known Activations