© 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. 40-GEMMASCOPE-2-RES-65K
    7. 1043
    Prev
    Next
    INDEX
    Explanations

    to + verb phrase

    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_40_width_65k_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
     AUC
    0.42
     bien
    0.39
    ός
    0.38
    AUC
    0.38
    genden
    0.38
     oblivious
    0.37
    ף
    0.37
    তেন
    0.37
    ladı
    0.37
    ")),
    0.36
    POSITIVE LOGITS
     everything
    0.42
     bites
    0.40
     Bites
    0.39
     bitterness
    0.38
    everything
    0.37
    mités
    0.37
     sacrifices
    0.36
    Everything
    0.36
    탄
    0.36
     limitar
    0.35
    Activations Density 0.002%

    No Known Activations