© 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. 41-GEMMASCOPE-2-RES-262K
    7. 31293
    Prev
    Next
    INDEX
    Explanations

    salt

    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_all/layer_41_width_262k_l0_big
    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
     cpu
    0.46
     CPU
    0.45
    勮
    0.41
    strstr
    0.41
     Capsule
    0.40
     Request
    0.40
    Pow
    0.39
     HDD
    0.39
    cpu
    0.39
     xpath
    0.39
    POSITIVE LOGITS
     salt
    2.19
    salt
    1.95
    盐
    1.93
    Salt
    1.91
     Salt
    1.84
    鹽
    1.82
    塩
    1.77
     salts
    1.69
     SALT
    1.66
    SALT
    1.61
    Activations Density 0.011%

    No Known Activations