© 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. 3050
    Prev
    Next
    INDEX
    Explanations

    Host systems, computer, defense

    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
     acceptez
    -0.95
    هل
    -0.93
     óculos
    -0.91
    ఇ
    -0.90
    回到
    -0.88
     вдох
    -0.88
    ไทย
    -0.87
    i
    -0.86
     vorigen
    -0.85
    南浔
    -0.85
    POSITIVE LOGITS
     Host
    1.54
     host
    1.42
    pital
    1.38
    esses
    1.33
    getHost
    1.28
    Host
    1.14
     HOST
    1.10
    host
    1.07
     hosts
    1.04
    achy
    1.03
    Activations Density 0.021%

    No Known Activations