© 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. 31-GEMMASCOPE-2-RES-65K
    7. 10092
    Prev
    Next
    INDEX
    Explanations

    physical and metaphorical tightness

    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_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
    <0x0D>
    0.66
    忔
    0.57
    dib
    0.49
    طار
    0.49
    tral
    0.47
    悟
    0.47
     HomePage
    0.47
    trs
    0.47
     metade
    0.46
    sthe
    0.46
    POSITIVE LOGITS
     tighter
    1.41
     tight
    1.33
     tightness
    1.22
    Tight
    1.21
     Tight
    1.14
    tight
    1.10
     tightened
    1.10
     tighten
    1.07
     tightly
    1.05
    紧
    1.00
    Activations Density 0.096%

    No Known Activations