Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 821
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    故障
    1.25
     machined
    1.20
     예상
    1.12
     phishing
    1.11
     hitbox
    1.09
     snappy
    1.08
    捅
    1.07
     수출
    1.07
     unsightly
    1.07
     slowdown
    1.07
    POSITIVE LOGITS
     spiritual
    1.90
     religious
    1.84
     religion
    1.61
     Spiritual
    1.61
     Religious
    1.60
     spirituality
    1.58
     espiritual
    1.55
    spiritual
    1.53
    religious
    1.52
     theological
    1.48
    Activations Density 1.765%

    No Known Activations