© 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. 41-GEMMASCOPE-2-RES-16K
    7. 10260
    Prev
    Next
    INDEX
    Explanations

    mother

    np_max-act-logits · gemini-2.5-flash-lite

    mother

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_16k_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
     সমৃদ্ধ
    0.54
     Murcia
    0.54
    ิว
    0.54
     relevant
    0.53
    짭
    0.51
    estens
    0.50
    efully
    0.50
     Schaden
    0.49
     Mull
    0.49
    ssch
    0.49
    POSITIVE LOGITS
    hood
    1.16
    hetical
    1.16
    hesized
    1.16
     hood
    1.09
    heses
    1.06
    Hood
    0.99
    hetically
    0.89
    뻘
    0.86
    hesis
    0.80
     hoods
    0.76
    Activations Density 0.063%

    No Known Activations