© 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. 176126
    Prev
    Next
    INDEX
    Explanations

    individual research

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

    potential spot, field., and overthrow, Officers in, will likely, step towards

    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
    li
    0.47
    rbuf
    0.46
     стекла
    0.45
     gur
    0.42
    션
    0.42
    cs
    0.42
    scri
    0.41
     સમાચાર
    0.41
    setDate
    0.41
     кров
    0.41
    POSITIVE LOGITS
    ≈
    0.51
    。“
    0.48
     priesthood
    0.47
     efficiencies
    0.47
     Efficiency
    0.46
    డ్డ
    0.46
     reflectivity
    0.46
    。
    0.46
     στη
    0.46
    達到
    0.45
    Activations Density 0.001%

    No Known Activations