© 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. 157468
    Prev
    Next
    INDEX
    Explanations

    watched over, security station, improving abilities

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

    common words and concepts

    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
    e
    0.75
    i
    0.57
    er
    0.56
    s
    0.54
    or
    0.52
    ul
    0.51
    id
    0.51
    es
    0.50
    el
    0.50
    en
    0.49
    POSITIVE LOGITS
     그리고
    0.52
     interleukin
    0.49
     đau
    0.48
     hypothyroidism
    0.45
     kişinin
    0.44
     traumas
    0.44
    ।”
    0.43
     부탁
    0.42
     sabotage
    0.42
     そして
    0.42
    Activations Density 0.001%

    No Known Activations