© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 17659
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings

    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
     pronoun
    0.43
    권
    0.42
     dedic
    0.41
    цька
    0.41
     аллер
    0.40
     allergies
    0.39
    ራሉ
    0.39
    縄
    0.39
    権
    0.39
     pulley
    0.39
    POSITIVE LOGITS
     hex
    1.09
     hexadecimal
    1.02
     Hex
    1.01
    hex
    0.95
    Hex
    0.94
     HEX
    0.84
    HEX
    0.79
     hexa
    0.78
    HexString
    0.76
     hexane
    0.61
    Activations Density 0.141%

    No Known Activations