Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 4196
    Prev
    Next
    INDEX
    Explanations

    climate, fire, extreme, highly, multi, latex

    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
     sababu
    0.46
    كلة
    0.46
     kojoj
    0.45
    kD
    0.45
     Başkanı
    0.43
    两
    0.43
    :],
    0.42
     menjalani
    0.42
    అ
    0.42
    :]
    0.41
    POSITIVE LOGITS
     are
    0.50
     actuelle
    0.46
     fluctuates
    0.46
     incend
    0.44
     혹은
    0.44
     documentaries
    0.44
     continua
    0.43
    ну
    0.42
     эту
    0.42
     використову
    0.41
    Activations Density 0.682%

    No Known Activations