Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 14022
    Prev
    Next
    INDEX
    Explanations

    open weights model

    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_16_width_262k_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
    ة
    0.81
    ай
    0.75
    ер
    0.74
    し
    0.70
    ি
    0.67
     ditambah
    0.64
    {//
    0.64
    ী
    0.63
    िफ
    0.63
    ো
    0.63
    POSITIVE LOGITS
     Weights
    0.71
    k
    0.66
    java
    0.65
     Hern
    0.65
     Kosovo
    0.64
     on
    0.63
     pastor
    0.63
     Florian
    0.63
     Si
    0.62
    weights
    0.62
    Activations Density 0.022%

    No Known Activations