© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3715
    Prev
    Next
    INDEX
    Explanations

    bed, bedding, pillows

    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_29_width_65k_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
     ガラス
    0.71
    irdi
    0.69
     cyclotron
    0.66
     kalem
    0.66
     Jerez
    0.65
    Ω
    0.65
     পরিচয়
    0.65
    嘬
    0.65
     sidang
    0.64
     юни
    0.64
    POSITIVE LOGITS
     bed
    3.10
     mattress
    3.06
     bedding
    2.98
     beds
    2.85
     mattresses
    2.76
     pillows
    2.76
     Bed
    2.63
     pillow
    2.63
    Bed
    2.61
     Beds
    2.53
    Activations Density 0.144%

    No Known Activations