© 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. 29-GEMMASCOPE-2-RES-262K
    7. 148838
    Prev
    Next
    INDEX
    Explanations

    spaciousness and room

    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_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
    spike
    0.66
    verting
    0.61
    ringe
    0.61
    wand
    0.60
    regel
    0.59
    嗟
    0.59
     pulver
    0.58
    வுகள்
    0.58
    GAM
    0.57
    owa
    0.57
    POSITIVE LOGITS
     luxurious
    0.92
     sleek
    0.92
     Luxurious
    0.89
     spacious
    0.88
     Spacious
    0.87
     Stylish
    0.85
    긋
    0.85
    acyj
    0.84
     élég
    0.84
     роско
    0.84
    Activations Density 0.003%

    No Known Activations