© 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. 6363
    Prev
    Next
    INDEX
    Explanations

    growing up, range in, GB, document, Risk Assessment

    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
     نتكلم
    0.45
    GF
    0.42
     ત્યાર
    0.42
    erta
    0.41
     ಸದ
    0.41
    ತ
    0.41
     ሽ
    0.41
    Saldo
    0.41
    𝑭
    0.41
     передба
    0.40
    POSITIVE LOGITS
    া
    0.46
    selves
    0.45
     solve
    0.43
     themselves
    0.41
     uspe
    0.40
     migrant
    0.40
    내
    0.40
     laborious
    0.39
     knowledgeable
    0.39
     solution
    0.39
    Activations Density 0.014%

    No Known Activations