© 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. 60233
    Prev
    Next
    INDEX
    Explanations

    X-UA-Compatible

    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
     takeover
    -0.81
     proy
    -0.75
    Stem
    -0.74
    enddo
    -0.73
    leer
    -0.73
    Manhattan
    -0.71
     Stem
    -0.71
     Controls
    -0.71
    endfor
    -0.69
    绳
    -0.68
    POSITIVE LOGITS
    leč
    0.67
    berley
    0.67
    estructuras
    0.66
    avelength
    0.66
     Mühe
    0.66
     Nevis
    0.65
    riva
    0.64
    sentinel
    0.64
    powiedz
    0.64
     expectant
    0.64
    Activations Density 0.053%

    No Known Activations