© 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. 109899
    Prev
    Next
    INDEX
    Explanations

    make it to playoffs

    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
    ἰ
    -1.10
     prawie
    -1.07
    essentially
    -1.05
     alltid
    -0.96
     praticamente
    -0.95
     Apakah
    -0.93
     morir
    -0.93
     acceder
    -0.92
    細い
    -0.92
     monto
    -0.90
    POSITIVE LOGITS
     big
    1.38
     this
    1.25
     hopefully
    1.22
     mindestens
    1.18
     very
    1.18
     if
    1.16
     again
    1.13
     akár
    1.12
     at
    1.08
     good
    1.07
    Activations Density 0.041%

    No Known Activations