© 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. 40-GEMMASCOPE-2-RES-262K
    7. 8040
    Prev
    Next
    INDEX
    Explanations

    Gemma team creators, open weights model

    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_40_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
     veines
    0.45
    မျက်
    0.43
     gezien
    0.41
     букмекер
    0.41
     comprado
    0.41
     للس
    0.40
    ...*/
    0.40
    把
    0.40
     lvl
    0.40
     vegas
    0.40
    POSITIVE LOGITS
     creators
    0.89
     researchers
    0.84
     developers
    0.81
     Researchers
    0.80
     OpenAI
    0.75
    Researchers
    0.74
    公開
    0.73
     Developers
    0.73
     team
    0.71
     scientists
    0.71
    Activations Density 0.184%

    No Known Activations