© 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. 13463
    Prev
    Next
    INDEX
    Explanations

    technical concepts

    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
     Pec
    0.56
    خص
    0.53
    鴻
    0.53
    }_{{\
    0.52
     bottleneck
    0.51
    ab
    0.50
    attery
    0.50
    ennen
    0.50
     الاخت
    0.49
     Alkal
    0.49
    POSITIVE LOGITS
     депозиттик
    0.58
     रिवा
    0.57
    𝙄
    0.55
     रीजनिंग
    0.55
     convinc
    0.55
     Cavs
    0.55
    cco
    0.54
     выво
    0.54
     retir
    0.53
     informática
    0.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.