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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 165173
    Prev
    Next
    INDEX
    Explanations

    first guide new

    np_acts-logits-general · gemini-2.5-flash-lite

    these are, shop around, who influences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    With
    0.50
    '><
    0.46
     कोशिका
    0.45
    }=\{
    0.44
    ระหว่าง
    0.44
     म्यू
    0.44
    ’)
    0.44
    '>
    0.44
    Unfortunately
    0.44
    动的
    0.44
    POSITIVE LOGITS
    jud
    0.56
     looting
    0.51
     jud
    0.50
     emanc
    0.49
     Jud
    0.48
     bashing
    0.46
     클릭
    0.46
    LING
    0.45
    畅
    0.45
     quarant
    0.45
    Activations Density 0.000%

    No Known Activations