© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8361
    Prev
    Next
    INDEX
    Explanations

    apartments and networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    élect
    0.51
    granular
    0.46
    forgettable
    0.46
    SpriteCollision
    0.46
    𝐞
    0.46
    Insp
    0.45
    性能
    0.44
    𝗻
    0.44
     گذ
    0.44
    𝐦
    0.44
    POSITIVE LOGITS
     Apartment
    0.58
     Apartments
    0.57
     apartment
    0.57
     ON
    0.54
     apartments
    0.53
     Android
    0.52
     Hotels
    0.52
     apartamentos
    0.50
     apartamento
    0.49
     Earrings
    0.49
    Activations Density 0.010%

    No Known Activations