© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 3072
    Prev
    Next
    INDEX
    Explanations

    mother's day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    Bună
    0.86
    CHE
    0.80
    СО
    0.78
    یث
    0.76
    ერ
    0.76
    泮
    0.76
    ➋
    0.75
     شفاف
    0.75
     préalable
    0.74
    Imidazole
    0.74
    POSITIVE LOGITS
    뻘
    1.55
    hetical
    1.50
    hood
    1.41
    heses
    1.17
    辈
    1.13
     filial
    1.10
    hesized
    1.09
    বধূ
    1.09
     remar
    1.07
    hetically
    1.07
    Activations Density 0.078%

    No Known Activations