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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82318
    Prev
    Next
    INDEX
    Explanations

    license and conditions

    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
     over
    -0.93
    MATERIALS
    -0.68
     Interfer
    -0.68
    oole
    -0.67
    pwd
    -0.67
     chứ
    -0.66
     Mandi
    -0.65
     enforceable
    -0.65
     πάνω
    -0.65
    つき
    -0.65
    POSITIVE LOGITS
    웍
    0.71
     presos
    0.71
    ⠠
    0.68
    设计师
    0.67
    sq
    0.66
    })(\
    0.66
     Hea
    0.65
    tuta
    0.64
    יצ
    0.63
    koh
    0.63
    Activations Density 0.054%

    No Known Activations