© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99192
    Prev
    Next
    INDEX
    Explanations

    Mal prefix

    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
     prosperity
    -0.79
     delusions
    -0.78
    garis
    -0.76
    settling
    -0.72
     Prosperity
    -0.72
    pA
    -0.71
     finally
    -0.71
    ARROLLO
    -0.70
    dV
    -0.70
    ைக
    -0.69
    POSITIVE LOGITS
    Mal
    1.13
     Mal
    1.05
     afore
    1.02
     mal
    0.90
    chauen
    0.88
    értel
    0.86
    ahead
    0.85
    strom
    0.82
     MAL
    0.82
     utiliser
    0.79
    Activations Density 0.044%

    No Known Activations