© 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. 2933
    Prev
    Next
    INDEX
    Explanations

    stage startup, weights AI

    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
     risking
    0.44
    𝘬
    0.38
     côté
    0.37
     ulike
    0.37
    很多
    0.36
    寒い
    0.36
     різних
    0.36
    制度
    0.36
     करणे
    0.35
     disgraceful
    0.35
    POSITIVE LOGITS
     multipurpose
    0.41
     plywood
    0.37
     multifunctional
    0.33
     (!)
    0.33
    (!)
    0.33
     (>
    0.32
     veterinary
    0.31
     thermoplastic
    0.31
    OSA
    0.30
    ITAS
    0.30
    Activations Density 0.423%

    No Known Activations