© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109836
    Prev
    Next
    INDEX
    Explanations

    following

    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
    خاذ
    -0.96
    🔲
    -0.89
     senare
    -0.82
     später
    -0.82
    Later
    -0.82
    Pele
    -0.79
     Потом
    -0.79
     LATER
    -0.77
     Erkrank
    -0.75
    жнему
    -0.75
    POSITIVE LOGITS
     following
    8.56
    following
    6.22
    Following
    6.16
     Following
    5.91
     FOLLOWING
    5.31
     siguientes
    4.16
     seguintes
    3.94
     folgenden
    3.75
     seguenti
    3.61
     siguiente
    3.41
    Activations Density 0.545%

    No Known Activations