© 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. 1903
    Prev
    Next
    INDEX
    Explanations

    source links

    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
     monoxide
    0.36
    lees
    0.36
     accelerates
    0.34
    le
    0.34
    z
    0.34
    POs
    0.34
     hills
    0.33
     delusion
    0.33
    and
    0.33
    #,
    0.33
    POSITIVE LOGITS
     Перейти
    0.68
     ঝাঁপ
    0.54
     http
    0.48
     "'
    0.44
     تعدى
    0.44
     https
    0.43
     Ка
    0.42
     Ibid
    0.41
     Пу
    0.41
     Saltar
    0.41
    Activations Density 0.001%

    No Known Activations