© 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. 1820
    Prev
    Next
    INDEX
    Explanations

    scripting

    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
    ি
    2.79
    साइटी
    2.52
    ğlu
    2.50
    सायटी
    2.50
    "+
    2.49
    বিত্র
    2.48
    𝓹
    2.48
    itaires
    2.47
    ität
    2.46
    ঝ
    2.38
    POSITIVE LOGITS
     counteract
    2.91
    ting
    2.84
    roleum
    2.76
    lerin
    2.72
    xture
    2.57
    leri
    2.55
    tttt
    2.51
    ropolitan
    2.49
    lerle
    2.46
    rium
    2.43
    Activations Density 0.389%

    No Known Activations