© 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. 315
    Prev
    Next
    INDEX
    Explanations

    de la, Kruk, Péchet

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    deserialize
    2.31
     grasslands
    2.09
     forestry
    2.05
    ᚄ
    2.05
     grassland
    1.99
     decline
    1.96
     cyberpunk
    1.95
    
    1.92
    featur
    1.90
     collapse
    1.89
    POSITIVE LOGITS
     macam
    1.69
    keb
    1.53
    فاظ
    1.52
    বাহ
    1.50
     Abl
    1.49
    \/
    1.44
    ®
    1.42
    لز
    1.42
     ابت
    1.42
    </i>
    1.41
    Activations Density 0.000%

    No Known Activations