© 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. 195784
    Prev
    Next
    INDEX
    Explanations

    achieve your goal

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

    unexpected stranding

    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
     (*
    0.46
     after
    0.46
    bound
    0.41
     dopo
    0.41
     Puoi
    0.40
     Menu
    0.40
     Bound
    0.40
    aneous
    0.40
     कष्ट
    0.39
    hhhh
    0.39
    POSITIVE LOGITS
    ט
    0.48
    ס
    0.46
    ਬ
    0.46
    ༩
    0.44
    รัฐ
    0.44
    ژه
    0.43
    צ
    0.43
    ༨
    0.43
    ੰ
    0.42
    يد
    0.42
    Activations Density 0.000%

    No Known Activations