© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118822
    Prev
    Next
    INDEX
    Explanations

    chart axes and ranges

    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
     tā
    -0.78
     Pagina
    -0.75
    DAB
    -0.74
    部
    -0.74
    nically
    -0.74
     hvilket
    -0.73
    éti
    -0.72
     phấn
    -0.69
    Fet
    -0.68
     hongos
    -0.68
    POSITIVE LOGITS
     ziehen
    0.88
     CH
    0.83
     Chart
    0.80
    ʁ
    0.78
     defoli
    0.76
    Chart
    0.74
    伸ば
    0.73
    𝘁
    0.73
    騒
    0.73
     ZERO
    0.72
    Activations Density 0.009%

    No Known Activations