© 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. 119752
    Prev
    Next
    INDEX
    Explanations

    creative assets, content, or planning

    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
     Probleme
    0.60
    лади
    0.55
    ܀
    0.54
     probleme
    0.53
    夎
    0.53
     Zusätzlich
    0.51
    пат
    0.51
     problemas
    0.50
     상당
    0.50
    <unused465>
    0.50
    POSITIVE LOGITS
    ss
    0.46
     courteous
    0.45
     cryptographic
    0.41
     seized
    0.40
     fans
    0.40
     military
    0.40
     seizing
    0.40
     polite
    0.40
     iridescent
    0.39
     commemorative
    0.39
    Activations Density 0.000%

    No Known Activations