© 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. 200604
    Prev
    Next
    INDEX
    Explanations

    closures, eligibility, ratio, inhabiting

    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
     אבל
    0.46
     उपलब्
    0.42
    чис
    0.41
    ccione
    0.41
    (',',$
    0.40
     offenses
    0.40
    Bever
    0.40
    Depos
    0.40
    bnb
    0.40
     ಆದರೆ
    0.39
    POSITIVE LOGITS
     Tik
    0.56
     velké
    0.54
     Kab
    0.52
     P
    0.51
     vysok
    0.51
     importante
    0.49
     Kay
    0.49
     Rocky
    0.48
     větší
    0.48
     groot
    0.48
    Activations Density 0.003%

    No Known Activations