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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31307
    Prev
    Next
    INDEX
    Explanations

    notice or license agreement

    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
     granat
    -0.91
     etui
    -0.90
    🤩
    -0.84
    Ѳ
    -0.82
    :,,
    -0.82
     antena
    -0.81
     niggas
    -0.81
     naturen
    -0.81
     alber
    -0.80
     ★★★★
    -0.80
    POSITIVE LOGITS
    お手
    0.82
    벽
    0.79
     zufried
    0.78
    ピュー
    0.77
     —
    0.76
     якого
    0.76
     cenderung
    0.75
     angefü
    0.74
     विश
    0.74
     davon
    0.73
    Activations Density 0.214%

    No Known Activations