© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110442
    Prev
    Next
    INDEX
    Explanations

    planets and celestial bodies

    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
    IGER
    -0.83
    лата
    -0.81
     energia
    -0.80
     الكهرب
    -0.79
     fotografia
    -0.77
     bandoulière
    -0.76
     ethernet
    -0.76
     pagar
    -0.74
     unicorns
    -0.74
    USERNAME
    -0.74
    POSITIVE LOGITS
     planet
    2.70
     planets
    2.52
    planet
    1.92
     Planet
    1.73
     плане
    1.66
     planetary
    1.55
    Planet
    1.48
     Planets
    1.43
     PLANET
    1.42
    planets
    1.38
    Activations Density 0.022%

    No Known Activations