© 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. 149217
    Prev
    Next
    INDEX
    Explanations

    in dependence on

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

    state-of-the-art models

    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
     Zusätzlich
    0.51
     України
    0.48
     державних
    0.47
    棂
    0.47
    颀
    0.46
    靔
    0.46
     Украї
    0.46
     території
    0.46
     Moderators
    0.46
     Logs
    0.45
    POSITIVE LOGITS
    かっ
    0.52
     decap
    0.44
    ]^{
    0.43
    footnotes
    0.42
    ریان
    0.41
    에요
    0.41
    notebook
    0.41
    namely
    0.41
    pInBuffer
    0.40
    nourished
    0.40
    Activations Density 0.001%

    No Known Activations