© 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
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13445
    Prev
    Next
    INDEX
    Explanations

    negative states

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    TableView
    0.64
    ә
    0.61
    及
    0.56
    ússia
    0.56
    ＆
    0.55
    Tens
    0.55
    DataAnnotations
    0.55
    }°
    0.54
    eylon
    0.54
     برنامه
    0.54
    POSITIVE LOGITS
     tyranny
    1.43
     mania
    1.41
     paranoia
    1.34
    ophobia
    1.32
     hysteria
    1.31
     psychosis
    1.29
     hegemony
    1.26
     madness
    1.25
     fallacy
    1.24
     frenzy
    1.23
    Activations Density 0.191%

    No Known Activations