© 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. 1955
    Prev
    Next
    INDEX
    Explanations

    September in seasonal ranges

    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
    فت
    2.78
     senjata
    2.67
     جبر
    2.60
    sm
    2.59
    </h4>
    2.57
    obot
    2.54
    ays
    2.49
    žu
    2.47
    笂
    2.38
    asting
    2.38
    POSITIVE LOGITS
    ු
    3.90
    iunea
    3.14
    ˏ
    2.98
    𝙩
    2.96
    𝙣
    2.94
    i
    2.92
    iella
    2.87
    н
    2.83
    𝙡
    2.81
    𝙞
    2.75
    Activations Density 0.015%

    No Known Activations