© 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. 20968
    Prev
    Next
    INDEX
    Explanations

    use pseudocode process

    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
    I
    0.48
     residing
    0.44
    муж
    0.44
    de
    0.43
    де
    0.43
     пово
    0.41
     على
    0.41
     రక్త
    0.41
    و
    0.41
     ജീവിത
    0.40
    POSITIVE LOGITS
     使っ
    0.54
    ’
    0.50
     quantitatively
    0.49
    usian
    0.48
     ทำให้
    0.46
    observable
    0.46
     Rwanda
    0.46
    inen
    0.45
     ♪
    0.45
     やっぱり
    0.45
    Activations Density 0.007%

    No Known Activations