© 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. 58110
    Prev
    Next
    INDEX
    Explanations

    political attacks and messaging

    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
    jenih
    -0.85
    biased
    -0.85
    iera
    -0.84
    zine
    -0.84
     pemandangan
    -0.83
     bia
    -0.82
     вме
    -0.82
     Brescia
    -0.81
    unnel
    -0.80
     catalyst
    -0.80
    POSITIVE LOGITS
     attack
    1.63
     attacks
    1.59
     attacking
    1.49
     messaging
    1.45
     attacked
    1.40
     Attack
    1.33
    attack
    1.16
    Attack
    1.11
     message
    1.10
    Attacking
    1.06
    Activations Density 0.078%

    No Known Activations