© 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. 16-GEMMASCOPE-2-RES-262K
    4. 21026
    Prev
    Next
    INDEX
    Explanations

    quick brown fox jumps

    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
     validType
    0.59
    明确
    0.58
     comporte
    0.57
    强势
    0.56
    睺
    0.56
     бону
    0.55
     propylene
    0.55
    avacak
    0.55
     compétences
    0.54
    EMY
    0.53
    POSITIVE LOGITS
     k
    0.64
    4
    0.61
    left
    0.58
    period
    0.58
    footer
    0.56
    histo
    0.56
    situation
    0.56
    iteration
    0.55
    ----------------
    0.55
    union
    0.55
    Activations Density 0.071%

    No Known Activations