© 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. 17796
    Prev
    Next
    INDEX
    Explanations

    connecting concepts

    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
     मिर
    0.45
     serveur
    0.44
     ম
    0.44
     rayonnement
    0.41
    swadian
    0.41
    )});
    0.41
     канал
    0.40
    ϊ
    0.40
    пин
    0.40
    цова
    0.40
    POSITIVE LOGITS
    Duplicate
    0.48
     apathy
    0.48
     dieses
    0.47
     stets
    0.47
     ripet
    0.47
     annivers
    0.44
    arel
    0.44
    apped
    0.43
     quadrat
    0.42
     fruit
    0.42
    Activations Density 0.019%

    No Known Activations