© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40299
    Prev
    Next
    INDEX
    Explanations

    sensitive topics and policy violations

    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
    GTBase
    0.46
    
    0.45
    ிருக்கிறார்
    0.44
     سلاټونه
    0.43
     χρή
    0.43
    '`--'`--
    0.42
     Εκ
    0.42
    𝙧
    0.41
    foregroundView
    0.41
     θέ
    0.41
    POSITIVE LOGITS
    '
    0.55
     with
    0.50
     kaum
    0.46
    et
    0.44
     solely
    0.42
     database
    0.41
    ל
    0.41
     this
    0.41
     same
    0.40
     too
    0.40
    Activations Density 0.000%

    No Known Activations