© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 233
    Prev
    Next
    INDEX
    Explanations

    purpose and ethereal

    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
    assertEqual
    1.45
     unst
    1.41
     saver
    1.34
    djangoproject
    1.28
    intestinal
    1.27
    osperm
    1.21
    gült
    1.21
    (['
    1.21
     зару
    1.21
     mediated
    1.19
    POSITIVE LOGITS
    aturally
    2.74
    ombres
    2.58
     пусто
    2.58
    ixar
    2.48
    ectar
    2.47
     finito
    2.41
    采集
    2.41
     lugar
    2.39
    ihilation
    2.38
     jednocześnie
    2.38
    Activations Density 0.088%

    No Known Activations