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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7827
    Prev
    Next
    INDEX
    Explanations

    GET followed by system names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    you
    -1.20
    銪
    -1.11
    不够
    -1.10
    ed
    -1.09
    to
    -1.09
    e
    -1.07
    Takk
    -1.05
    𝐲
    -1.05
    Is
    -1.04
    Fär
    -1.02
    POSITIVE LOGITS
     rid
    2.25
     acquainted
    1.34
    tings
    1.34
    tting
    1.20
    不到
    1.16
    timg
    1.16
    tedì
    1.14
     ready
    1.09
    ipy
    1.06
    cciale
    1.04
    Activations Density 0.036%

    No Known Activations