© 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. 40-GEMMASCOPE-2-RES-65K
    7. 48514
    Prev
    Next
    INDEX
    Explanations

    salt crystals

    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_40_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
    cées
    0.37
    🍔
    0.37
    ком
    0.36
    ங்கா
    0.36
     पै
    0.35
    क्लेव
    0.35
    kapet
    0.35
    眷
    0.35
     trova
    0.35
     Smiley
    0.34
    POSITIVE LOGITS
     crystals
    2.58
     crystal
    2.41
     Crystals
    2.25
    crystals
    2.19
     crystall
    2.17
     crystallization
    2.17
    crystal
    2.03
    晶
    2.00
    Crystal
    1.99
     Crystal
    1.98
    Activations Density 0.051%

    No Known Activations