© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 12298
    Prev
    Next
    INDEX
    Explanations

    SQL SELECT statements

    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
     sprayed
    1.40
     twice
    1.31
    สอง
    1.18
     spraying
    1.17
    อยู่ที่
    1.16
     ​​
    1.15
    റ
    1.14
     initially
    1.13
     హై
    1.12
     }=
    1.11
    POSITIVE LOGITS
     aneur
    1.93
    ρί
    1.89
     assertFalse
    1.83
     εκεί
    1.77
    αλλ
    1.75
     αυτό
    1.72
     invertebrate
    1.72
    ophyllum
    1.71
    крови
    1.70
    엽
    1.70
    Activations Density 0.038%

    No Known Activations