© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 49276
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and notation

    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
     thumbnailUrl
    0.51
    {\'
    0.49
     gastronomic
    0.48
    ‍
    0.47
     correspondingly
    0.45
     jurídica
    0.45
     һәм
    0.44
     envisaged
    0.44
     subscrib
    0.44
    \'{
    0.44
    POSITIVE LOGITS
    ٹ
    0.53
     Gave
    0.50
     veulent
    0.50
     acero
    0.48
     پہلے
    0.46
     ALWAYS
    0.46
     determina
    0.46
     tuvo
    0.46
    Nope
    0.45
     avaient
    0.45
    Activations Density 0.052%

    No Known Activations