© 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. 16-GEMMASCOPE-2-RES-262K
    7. 86595
    Prev
    Next
    INDEX
    Explanations

    parts of words or suffixes

    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_16_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
     azok
    0.57
     elke
    0.55
     fragen
    0.53
     akkor
    0.53
    ৭
    0.53
     smrt
    0.52
     Kik
    0.51
    nå
    0.51
     zes
    0.50
     aant
    0.50
    POSITIVE LOGITS
    dasarkan
    0.57
    reciation
    0.53
    мати
    0.52
    inės
    0.52
     도입
    0.51
    дования
    0.48
    ೇವಿನ
    0.46
    γχ
    0.46
    gado
    0.46
    ੈ
    0.46
    Activations Density 0.000%

    No Known Activations