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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 140
    Prev
    Next
    INDEX
    Explanations

    unique structure

    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
    イント
    -0.77
    Ն
    -0.76
    Spatial
    -0.74
    fection
    -0.74
    actionBar
    -0.73
    UserModel
    -0.72
     Ish
    -0.70
     المض
    -0.69
    veien
    -0.69
     Spatial
    -0.68
    POSITIVE LOGITS
     nationalities
    0.77
    Annotations
    0.75
     وفا
    0.74
     incidents
    0.73
     nevoie
    0.72
    ifornie
    0.69
     করে
    0.69
    オリーブ
    0.68
     Speak
    0.68
    UMENTS
    0.67
    Activations Density 0.027%

    No Known Activations