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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 17680
    Prev
    Next
    INDEX
    Explanations

    comparison tables

    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
    цыяна
    0.51
    راضي
    0.42
     guzt
    0.41
    蔵
    0.41
     %>/
    0.40
    marshalN
    0.40
     valor
    0.40
     말미암
    0.40
    禳
    0.39
     supernatants
    0.39
    POSITIVE LOGITS
    م
    0.47
    }
    0.45
    ش
    0.42
     SPOT
    0.41
    Bonjour
    0.40
     Kees
    0.40
    ্লে
    0.39
     Marca
    0.39
     Архивировано
    0.38
    OM
    0.38
    Activations Density 0.007%

    No Known Activations