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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1357
    Prev
    Next
    INDEX
    Explanations

    places

    np_acts-logits-general · gemini-2.5-flash-lite

    types of places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scalar
    0.41
    芾
    0.40
     alue
    0.39
     producten
    0.39
    地形
    0.36
    全体の
    0.36
     evt
    0.35
     `,
    0.35
     popolazione
    0.35
    日々
    0.35
    POSITIVE LOGITS
     offices
    1.24
     clubhouse
    1.20
     office
    1.10
    办公室
    1.10
     restaurant
    1.09
     showrooms
    1.09
     warehouse
    1.09
     cafeteria
    1.09
     showroom
    1.07
     pizzeria
    1.07
    Activations Density 1.065%

    No Known Activations