© 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. 40-GEMMASCOPE-2-RES-262K
    7. 8469
    Prev
    Next
    INDEX
    Explanations

    publication or problem

    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_40_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
    落
    0.41
    ሆነ
    0.39
     बीच
    0.39
     peine
    0.37
    divers
    0.37
    阶段
    0.37
    槑
    0.37
    անկ
    0.36
    猶
    0.36
     jak
    0.36
    POSITIVE LOGITS
     Publication
    0.48
     publication
    0.46
     publicação
    0.46
     pubs
    0.45
     editar
    0.43
    Publication
    0.42
     publier
    0.42
     publishes
    0.42
     publicación
    0.41
     Publishing
    0.41
    Activations Density 0.000%

    No Known Activations