© 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-262K
    7. 35975
    Prev
    Next
    INDEX
    Explanations

    ontological / deontological ethics

    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_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
     землі
    0.43
    affichage
    0.42
    𝐞
    0.41
    𝜇
    0.41
     ਜ਼
    0.41
     сцен
    0.40
    Scenic
    0.40
    ੇ
    0.40
     reseñas
    0.38
     పట్ట
    0.38
    POSITIVE LOGITS
     type
    0.51
    ujesz
    0.45
     Mode
    0.44
     somet
    0.42
     Mantra
    0.42
    ilov
    0.42
     command
    0.41
     obed
    0.41
     Shark
    0.41
     desiring
    0.41
    Activations Density 0.027%

    No Known Activations