© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13350
    Prev
    Next
    INDEX
    Explanations

    say rain

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     onboarding
    1.09
     👉
    1.08
     omnichannel
    1.08
     XNUMX
    1.07
     reimag
    1.05
     🙌
    1.05
     fintech
    1.02
     SDGs
    1.02
     macOS
    0.99
     👇
    0.99
    POSITIVE LOGITS
     supposition
    1.11
     excepting
    1.10
     presently
    0.99
     Presently
    0.98
     effectual
    0.97
     continual
    0.94
     সম্বন্ধ
    0.88
     solamente
    0.87
     effected
    0.85
     আরম্ভ
    0.85
    Activations Density 0.169%

    No Known Activations