© 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-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-65K
    4. 80
    Prev
    Next
    INDEX
    Explanations

    iridescent descriptive qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     الأ
    0.88
    abhuto
    0.84
    بالإنجليزية
    0.83
    valmentaja
    0.82
    itabbo
    0.82
    itabbam
    0.80
    甃
    0.79
     Literacy
    0.79
    unnumbered
    0.79
     جامعة
    0.78
    POSITIVE LOGITS
     and
    0.62
    /
    0.62
    2
    0.60
    1
    0.57
    0
    0.56
    is
    0.56
     tricks
    0.55
    i
    0.54
    ing
    0.53
     rather
    0.52
    Activations Density 0.000%

    No Known Activations