© 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. 109926
    Prev
    Next
    INDEX
    Explanations

    Official websites, press, tours

    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
     Basically
    -1.04
    รอบ
    -1.00
    大致
    -0.88
     octombrie
    -0.87
     overras
    -0.86
     Essentially
    -0.81
     our
    -0.81
    擘
    -0.81
     persön
    -0.80
    ledning
    -0.79
    POSITIVE LOGITS
     of
    1.09
     uniforme
    0.91
     somewhat
    0.88
     despi
    0.86
     emblema
    0.85
    sistence
    0.85
     complementa
    0.85
    somewhat
    0.83
     extraordin
    0.83
    known
    0.83
    Activations Density 0.025%

    No Known Activations