© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4562
    Prev
    Next
    INDEX
    Explanations

    perform signal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    fecha
    1.90
     atteggi
    1.83
     Fecha
    1.81
     czasie
    1.80
    揆
    1.78
    kwik
    1.72
    地點
    1.70
     luisant
    1.66
     Topical
    1.65
    夫妇
    1.65
    POSITIVE LOGITS
    迥
    1.84
    ‌هایی
    1.76
     respiration
    1.74
     separation
    1.67
    7
    1.67
     rejection
    1.62
    9
    1.56
     reproduction
    1.56
     diverge
    1.55
     combust
    1.53
    Activations Density 0.076%

    No Known Activations