© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41010
    Prev
    Next
    INDEX
    Explanations

    computers

    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_262k_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
     inactiv
    0.53
     measures
    0.40
     speciali
    0.40
     Salford
    0.40
     الته
    0.39
    戍
    0.39
     soli
    0.39
     implicitly
    0.39
    lje
    0.39
     Xuân
    0.38
    POSITIVE LOGITS
     конкурен
    0.48
     മറ്റ
    0.43
    ૦
    0.41
     табли
    0.41
    ба
    0.40
    ۰
    0.40
    charm
    0.40
    submit
    0.39
     shameful
    0.39
    ০
    0.38
    Activations Density 0.008%

    No Known Activations