© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1130
    Prev
    Next
    INDEX
    Explanations

    dialogue attribution

    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
    ถ
    0.76
    给我
    0.76
    ++)
    0.73
    ¹)
    0.69
    Cloud
    0.67
    -}
    0.66
    fichier
    0.66
    ड्रो
    0.65
    Streaming
    0.65
    -]
    0.65
    POSITIVE LOGITS
     says
    2.39
     according
    2.35
     said
    2.34
    他说
    2.18
    says
    2.13
    他說
    2.02
    said
    1.93
     According
    1.89
    她说
    1.88
    according
    1.85
    Activations Density 0.024%

    No Known Activations