© 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. 31-GEMMASCOPE-2-RES-262K
    7. 90763
    Prev
    Next
    INDEX
    Explanations

    sharing positive 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/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
     평
    0.40
    ↵
    0.39
    erais
    0.39
    வு
    0.38
     rash
    0.38
     रखकर
    0.37
    এব
    0.36
    qx
    0.36
     বা
    0.36
     রক্ষা
    0.36
    POSITIVE LOGITS
    𝙫
    0.60
    ንዳንድ
    0.55
     relatório
    0.50
     regelmäßig
    0.49
     juguete
    0.49
     материала
    0.49
     cárcel
    0.49
     regularly
    0.48
     einiger
    0.48
     einzige
    0.48
    Activations Density 0.004%

    No Known Activations