© 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. 98456
    Prev
    Next
    INDEX
    Explanations

    months followed by numbers or days

    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
    west
    -0.69
    wk
    -0.68
    Ownership
    -0.68
    priv
    -0.68
     Bravo
    -0.67
    ROSS
    -0.66
    рення
    -0.64
    znym
    -0.63
    charging
    -0.63
    Jsp
    -0.63
    POSITIVE LOGITS
    üsse
    0.74
    쩔
    0.69
     Einwilligung
    0.69
     consenso
    0.68
    配置
    0.68
    chaften
    0.67
     irritable
    0.67
     selaku
    0.66
    ͕
    0.66
    待ち
    0.66
    Activations Density 0.066%

    No Known Activations