© 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. 177966
    Prev
    Next
    INDEX
    Explanations

    money due

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

    limited, extremely, more

    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
    痛
    0.50
    сны
    0.46
     Indeed
    0.46
    ようになる
    0.45
    になり
    0.45
    vald
    0.43
    夕
    0.42
    的企业
    0.42
    的方法
    0.42
    なく
    0.41
    POSITIVE LOGITS
    tos
    0.59
     renferme
    0.54
    k
    0.52
    kenn
    0.52
     essentielles
    0.51
    cientes
    0.50
     quelcon
    0.50
    teles
    0.49
    ală
    0.49
     कार्रवाई
    0.49
    Activations Density 0.001%

    No Known Activations