© 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. 135003
    Prev
    Next
    INDEX
    Explanations

    financial discussions

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

    addressing this topic

    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
     centrifugation
    0.48
     同じ
    0.47
     হয়েছিল
    0.46
    quem
    0.46
     великолеп
    0.46
     смог
    0.46
     horizontale
    0.46
    噁
    0.46
     तापमान
    0.45
     गेला
    0.45
    POSITIVE LOGITS
     jobless
    0.48
     financial
    0.45
     financ
    0.44
     financiers
    0.43
     districts
    0.41
     hardworking
    0.41
     recast
    0.41
    财务
    0.41
     economic
    0.41
     preach
    0.41
    Activations Density 0.001%

    No Known Activations