© 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. 13-GEMMASCOPE-2-RES-16K
    7. 71
    Prev
    Next
    INDEX
    Explanations

    emoji at the start

    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_13_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
    玩笑
    1.25
    te
    1.19
    ใน
    1.18
    В
    1.15
     merito
    1.14
    เช่น
    1.11
    ensed
    1.10
    揮
    1.06
    さんの
    1.06
     conductores
    1.06
    POSITIVE LOGITS
    _{{\
    1.64
    ιστή
    1.61
    ,{\
    1.60
     =,
    1.53
    торы
    1.49
    }_{{\
    1.44
    筝
    1.42
    =")"
    1.42
     nudge
    1.42
     पेटीएम
    1.41
    Activations Density 0.000%

    No Known Activations