© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 56094
    Prev
    Next
    INDEX
    Explanations

    recognize and relate concepts

    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
    他的
    0.47
    チル
    0.47
    FreeBuf
    0.47
    Chin
    0.47
    გილ
    0.46
    ᅢ
    0.46
    Theoretical
    0.45
     стару
    0.45
    Celltype
    0.44
     його
    0.44
    POSITIVE LOGITS
     +
    0.54
     =
    0.53
     are
    0.52
     nearly
    0.44
     and
    0.44
     negocio
    0.44
     &
    0.43
     articul
    0.43
     eligible
    0.43
     qualifications
    0.43
    Activations Density 0.001%

    No Known Activations