© 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. 48720
    Prev
    Next
    INDEX
    Explanations

    archetypes, tradition, precepts

    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
     पाण्डे
    0.51
    𝚞
    0.49
    𝚊
    0.47
    就會
    0.45
    燜
    0.44
    𝚘
    0.44
    જબ
    0.43
    يي
    0.43
    iverr
    0.43
    <0x89>
    0.43
    POSITIVE LOGITS
     Tradition
    0.48
     tradition
    0.47
     Anci
    0.47
     Annot
    0.44
     நிலைய
    0.42
     embl
    0.42
     shared
    0.41
     overcome
    0.41
     مقار
    0.41
     utterance
    0.40
    Activations Density 0.031%

    No Known Activations