© 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. 203055
    Prev
    Next
    INDEX
    Explanations

    money, rent, rubbish, surplus

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

    may not / maximize

    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
     ع
    0.53
     supre
    0.44
     와
    0.43
     فی
    0.43
    ‏
    0.42
     ق
    0.41
     غالب
    0.41
     Tesla
    0.41
     geology
    0.41
     ک
    0.40
    POSITIVE LOGITS
    দর্শ
    0.49
    কমার
    0.46
    todolist
    0.46
    зяй
    0.45
    শিশ
    0.45
    㽛
    0.45
    的這個
    0.44
     SOLD
    0.44
     нужда
    0.44
    aop
    0.43
    Activations Density 0.002%

    No Known Activations