Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 343
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ار
    0.31
     you
    0.29
     I
    0.27
     tulee
    0.26
     millas
    0.25
     formas
    0.25
    Apps
    0.24
     on
    0.24
    ot
    0.24
    iles
    0.24
    POSITIVE LOGITS
    นอก
    0.37
     oldukça
    0.36
    ко
    0.33
    ຢູ່ໃນ
    0.33
    з
    0.33
    که
    0.32
     αρκε
    0.31
     nên
    0.31
     настолько
    0.30
    т
    0.30
    Activations Density 5.647%

    No Known Activations