© 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. 72261
    Prev
    Next
    INDEX
    Explanations

    find more

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

    complex descriptor or context

    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
    减
    0.46
    )}_
    0.46
     Dole
    0.45
    })$,
    0.42
    ),"
    0.42
     \
    0.42
    宗教
    0.42
    教师
    0.41
    щений
    0.41
    rente
    0.40
    POSITIVE LOGITS
    ukan
    0.55
    निर्भर
    0.52
    いい
    0.49
    スペック
    0.49
    বিষ্য
    0.49
    ⓝ
    0.48
    Our
    0.48
     averiguar
    0.48
    瀆
    0.48
     aerodynamics
    0.47
    Activations Density 0.000%

    No Known Activations