© 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. 133700
    Prev
    Next
    INDEX
    Explanations

    cash and cash equivalents

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

    challenges, risks, injuries

    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
    演技
    0.47
    тету
    0.47
     Raha
    0.47
     Эд
    0.46
    ో
    0.46
    但在
    0.45
    ুটি
    0.44
    葭
    0.44
    赢得
    0.43
    "。
    0.43
    POSITIVE LOGITS
    is
    0.63
    ampl
    0.54
    ang
    0.49
    noble
    0.49
    bl
    0.48
    hung
    0.48
    ery
    0.47
     মিলিটারি
    0.46
    ab
    0.46
    ere
    0.45
    Activations Density 0.001%

    No Known Activations