© 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. 40497
    Prev
    Next
    INDEX
    Explanations

    forgetting or losing things

    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
     Neurol
    0.42
    KOV
    0.42
    <0x16>
    0.42
     Verständ
    0.42
     പ്രതീക്ഷ
    0.41
    ceph
    0.41
     Kxb
    0.41
     encephal
    0.39
     Cory
    0.39
     Św
    0.39
    POSITIVE LOGITS
     Rural
    0.38
     rurales
    0.38
    错
    0.37
     butcher
    0.37
     clothe
    0.37
    DOMstrings
    0.36
    啷
    0.35
    Allowed
    0.35
    Handle
    0.35
    Weather
    0.35
    Activations Density 0.019%

    No Known Activations