© 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. 30366
    Prev
    Next
    INDEX
    Explanations

    homing to zero position

    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
    remover
    -0.89
    utzung
    -0.82
    aplic
    -0.81
     Acesso
    -0.79
    Aplic
    -0.76
    Poder
    -0.75
    Escrit
    -0.75
    𝐐
    -0.75
    
    -0.75
    corazón
    -0.75
    POSITIVE LOGITS
     home
    2.08
    home
    1.70
     Home
    1.66
     HOME
    1.54
    Home
    1.51
    HOME
    1.41
     zero
    1.27
     homes
    1.22
     hom
    1.21
     Zero
    1.15
    Activations Density 0.026%

    No Known Activations