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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11394
    Prev
    Next
    INDEX
    Explanations

    concrete nouns and abstract concepts

    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_22/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
     अपने
    -1.10
    ₨
    -1.05
    Vanjske
    -0.96
    니까
    -0.95
     his
    -0.95
    יום
    -0.94
    UNRELATED
    -0.93
     yourself
    -0.92
    ７
    -0.91
    ᐈ
    -0.91
    POSITIVE LOGITS
     into
    1.12
     onto
    1.03
     differently
    0.99
     according
    0.96
    するように
    0.86
     unnoticed
    0.86
     ويت
    0.85
    scar
    0.84
     appris
    0.84
    となって
    0.83
    Activations Density 0.164%

    No Known Activations