© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 436
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    to
    2.01
    El
    1.96
    ت
    1.85
    ts
    1.85
    ¿
    1.78
    <bos>
    1.75
     o
    1.69
    EL
    1.69
    এর
    1.67
    trim
    1.67
    POSITIVE LOGITS
    ymmet
    2.94
    ymmetries
    2.24
    ymmetrical
    2.20
    sembled
    2.18
    ymmetry
    2.17
    ymmetric
    2.16
    phalt
    2.14
    sembling
    2.11
    pergillus
    2.06
     dusk
    2.05
    Activations Density 1.022%

    No Known Activations