© 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. 2563
    Prev
    Next
    INDEX
    Explanations

    Here's why

    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
    ো
    2.29
     headed
    2.24
    ो
    2.21
    ummers
    2.13
    ोलिक
    2.06
     Maintain
    2.05
     dringend
    2.04
    ues
    2.02
     नष्ट
    2.01
    োয়
    2.01
    POSITIVE LOGITS
    ◸
    2.23
    □
    2.19
     □
    2.09
    вку
    2.08
    Grady
    2.02
    此之外
    2.02
    Ott
    2.00
    場合がございます
    1.97
    ತ್ತು
    1.93
    FL
    1.92
    Activations Density 0.049%

    No Known Activations