© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9315
    Prev
    Next
    INDEX
    Explanations

    family and married relationships

    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_9_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
    *,
    0.94
    William
    0.92
    อื่นๆ
    0.92
    *-
    0.90
    غه
    0.89
    ے۔
    0.89
    vary
    0.88
    named
    0.86
    fourth
    0.83
     William
    0.83
    POSITIVE LOGITS
    酥
    1.13
     booty
    1.11
    ﺘ
    1.07
    คาเดมี
    1.04
     rifles
    1.03
    汅
    1.03
    RenderTarget
    1.03
    หลด
    1.02
     Underwater
    1.01
     proporciona
    1.00
    Activations Density 0.001%

    No Known Activations