© 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. 9282
    Prev
    Next
    INDEX
    Explanations

    control, consistency, stability, informative, direct

    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
    squareup
    0.57
     лам
    0.50
    нт
    0.48
     vutta
    0.48
     буди
    0.48
     расска
    0.47
    >
    0.47
    ς
    0.46
     cheered
    0.46
    более
    0.46
    POSITIVE LOGITS
     MEAN
    0.49
    维护
    0.46
     Mean
    0.46
     OWN
    0.45
    所以我
    0.45
    𝐈
    0.45
    在我
    0.45
     MAINT
    0.44
    沒
    0.43
    基本上
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.