© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13719
    Prev
    Next
    INDEX
    Explanations

    environment or context

    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_16k_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
     finalised
    0.49
    ah
    0.45
    personalised
    0.43
    ani
    0.43
    peso
    0.42
    キ
    0.42
    ਓ
    0.42
    rs
    0.41
    俢
    0.41
     devoured
    0.40
    POSITIVE LOGITS
     environnement
    0.51
     ortam
    0.50
     formContext
    0.49
    UIKit
    0.49
     środow
    0.48
    环境
    0.48
    BuildContext
    0.47
     environment
    0.47
     ambiente
    0.45
     Umwelt
    0.45
    Activations Density 0.029%

    No Known Activations