© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121358
    Prev
    Next
    INDEX
    Explanations

    nostalgia and memories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_width_262k_l0_small_affine
    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
     Believe
    0.39
    Believe
    0.38
     Angry
    0.38
     ች
    0.36
    Angry
    0.35
     حرکت
    0.34
    💆
    0.34
    🧖
    0.34
    㷫
    0.34
    拯
    0.33
    POSITIVE LOGITS
     nostalgia
    0.78
     nostalg
    0.76
     memories
    0.70
     nostalgic
    0.68
     воспомина
    0.67
     reminis
    0.66
     recuerdos
    0.63
     reminisc
    0.61
     recollections
    0.61
     sentimental
    0.57
    Activations Density 0.036%

    No Known Activations