© 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. 70032
    Prev
    Next
    INDEX
    Explanations

    zim map

    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
    appendChild
    -0.82
    りんご
    -0.76
    äfts
    -0.75
     Ehre
    -0.75
    رة
    -0.75
    勐
    -0.75
    ziek
    -0.74
     slightest
    -0.73
     embora
    -0.71
    sspiel
    -0.71
    POSITIVE LOGITS
     osmotic
    0.81
     Riesen
    0.79
     안
    0.71
     safe
    0.70
     Aud
    0.68
    봄
    0.67
     secure
    0.67
    帮忙
    0.66
     Giant
    0.65
     auditory
    0.65
    Activations Density 0.053%

    No Known Activations