© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 29354
    Prev
    Next
    INDEX
    Explanations

    .png/.jpeg/svg

    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
    ₃
    0.45
    tDBOutput
    0.44
    nå
    0.43
     ecmaVersion
    0.42
    膾
    0.42
    餚
    0.41
     নারায়ণ
    0.41
    ettre
    0.39
    ዎን
    0.39
     nCharString
    0.39
    POSITIVE LOGITS
    they
    0.46
    butter
    0.44
        
    0.43
    funcionario
    0.41
    เพราะ
    0.41
    Ц
    0.40
    because
    0.40
    ”
    0.40
    Су
    0.39
     grade
    0.39
    Activations Density 0.014%

    No Known Activations