© 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. 235025
    Prev
    Next
    INDEX
    Explanations

    use and it

    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
    ผม
    0.54
    Event
    0.52
    Suite
    0.51
    Natalie
    0.49
    นอก
    0.49
    P
    0.49
    ὅ
    0.49
    拼接
    0.48
    ป
    0.48
    Med
    0.48
    POSITIVE LOGITS
     justifying
    0.56
     clarifying
    0.54
     compensating
    0.51
     reconciling
    0.51
     rearing
    0.50
     lubricating
    0.50
     hazy
    0.48
     consolidating
    0.48
     ৬৬
    0.47
     aware
    0.47
    Activations Density 0.001%

    No Known Activations