© 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
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1882
    Prev
    Next
    INDEX
    Explanations

    holds less moisture

    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
     (
    0.90
     w
    0.86
     favorite
    0.85
     little
    0.80
     so
    0.78
     defense
    0.78
     spirit
    0.74
     city
    0.73
    （
    0.72
     style
    0.72
    POSITIVE LOGITS
    𒁑
    1.30
     karotiti
    1.30
    𒄸
    1.29
    𒀤
    1.29
    adigane
    1.29
    𒈒
    1.29
    trprec
    1.29
    𒃷
    1.28
    <unused1324>
    1.28
    𒃮
    1.28
    Activations Density 0.000%

    No Known Activations