© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63825
    Prev
    Next
    INDEX
    Explanations

    improve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    수
    0.55
    یک
    0.54
    の話
    0.50
    에도
    0.50
    용
    0.48
    ２
    0.47
    מת
    0.47
    த
    0.46
    ਪਣ
    0.46
    ト
    0.46
    POSITIVE LOGITS
     animali
    0.46
     Diarsipkan
    0.44
     procrast
    0.44
     Рі
    0.42
     Security
    0.41
    
    0.41
    рії
    0.41
     কাঁদতে
    0.41
     crying
    0.40
     Lust
    0.40
    Activations Density 0.006%

    No Known Activations