© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12980
    Prev
    Next
    INDEX
    Explanations

    at least

    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
    энне
    2.85
    خیص
    2.64
    yll
    2.63
    رک
    2.60
    椹
    2.55
    नांतर
    2.49
    ᆸ
    2.44
    班牙
    2.39
    لای
    2.38
    SETS
    2.37
    POSITIVE LOGITS
     \\\
    2.35
    ்டர்
    2.16
    E
    2.15
    ன்றி
    2.14
    았다
    2.13
     sara
    2.11
    𝓷
    2.09
    ńcz
    2.06
    ້ມ
    2.05
     Males
    2.02
    Activations Density 0.005%

    No Known Activations