© 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. 93662
    Prev
    Next
    INDEX
    Explanations

    fabricated news

    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
    il
    0.54
    𝕦
    0.52
    జ
    0.50
    ią
    0.49
    ਜ
    0.48
     важное
    0.47
    ię
    0.46
     कों
    0.46
    у
    0.46
    𝚓
    0.45
    POSITIVE LOGITS
    IZE
    0.55
     blade
    0.45
    EY
    0.45
     haven
    0.44
     Matter
    0.44
     receptacle
    0.44
    IMM
    0.43
    VE
    0.43
     palm
    0.42
     Phase
    0.42
    Activations Density 0.004%

    No Known Activations