© 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-65K
    7. 4785
    Prev
    Next
    INDEX
    Explanations

    ancestry and origins

    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_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
    쫌
    0.39
     conservatively
    0.38
    加大
    0.38
     الطريقه
    0.37
    ке
    0.36
    formance
    0.35
     функ
    0.35
    ͟
    0.35
    把
    0.35
    }}}{\
    0.35
    POSITIVE LOGITS
     ancestors
    0.62
     histórias
    0.51
     origins
    0.50
     Geschichte
    0.49
     historii
    0.49
     lineages
    0.49
     roots
    0.49
     ancestor
    0.48
     ചരി
    0.47
     Origins
    0.47
    Activations Density 0.003%

    No Known Activations