© 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. 146139
    Prev
    Next
    INDEX
    Explanations

    President Elect

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

    financial and clinical contexts

    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
    සා
    0.46
    𝐡
    0.45
    قی
    0.44
    Từ
    0.44
    कं
    0.44
    Tony
    0.43
    ն
    0.42
    কার্য
    0.42
     Jody
    0.42
    food
    0.42
    POSITIVE LOGITS
     девя
    0.53
     ана
    0.49
     Побе
    0.49
     сигнала
    0.49
     Союза
    0.48
     bolet
    0.48
     клини
    0.46
     gesetz
    0.46
    ９
    0.46
     insolvent
    0.46
    Activations Density 0.000%

    No Known Activations