© 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. 20524
    Prev
    Next
    INDEX
    Explanations

    suffix

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

    suffix and prefix delimiters

    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
     bombe
    0.48
    ctive
    0.47
    acho
    0.43
    eko
    0.41
    nty
    0.40
    ونة
    0.39
    孺
    0.39
     trafficking
    0.38
     annih
    0.38
     gyn
    0.38
    POSITIVE LOGITS
    SUFFIX
    0.49
    $=\
    0.44
    ifndef
    0.42
    Suffix
    0.41
    ,-\
    0.41
    ॉक
    0.40
    缀
    0.40
    +"/
    0.40
    ਾਰ
    0.39
    新年
    0.39
    Activations Density 0.002%

    No Known Activations