© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 516
    Prev
    Next
    INDEX
    Explanations

    `software` and `systems` and their `integrity`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_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
     없고
    0.59
    性和
    0.59
     և
    0.58
     onların
    0.58
    했고
    0.57
     եւ
    0.57
    度和
    0.57
     their
    0.57
    0
    0.55
     или
    0.55
    POSITIVE LOGITS
     ஆகியவை
    1.02
     എന്നിവ
    1.01
     ஆகியவற்ற
    1.01
     sowie
    0.98
     serta
    0.88
     ஆகியோர்
    0.88
     ஆகிய
    0.80
     valamint
    0.74
     sekä
    0.73
     oraz
    0.71
    Activations Density 0.004%

    No Known Activations