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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14635
    Prev
    Next
    INDEX
    Explanations

    post-traumatic, post-war, post-conflict

    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
    й
    2.28
    त्व
    2.25
    itatea
    2.18
    issimo
    2.16
    izaciones
    2.14
     correctional
    2.14
    issime
    2.12
    лма
    2.07
    znam
    2.07
    な
    2.03
    POSITIVE LOGITS
    wenn
    1.70
    πα
    1.68
    ⁍
    1.68
     rượu
    1.67
    op
    1.67
     termen
    1.66
    AFTER
    1.63
     n
    1.62
    ਿਹ
    1.60
    })(
    1.59
    Activations Density 0.042%

    No Known Activations