© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11399
    Prev
    Next
    INDEX
    Explanations

    proper authorization

    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
    ന്‍റെ
    2.71
    ़
    2.70
    𝔰
    2.59
    <bos>
    2.59
    anska
    2.34
    ים
    2.32
    ড়ান্ত
    2.27
    řel
    2.24
    Bet
    2.20
    .'
    2.18
    POSITIVE LOGITS
    o
    2.52
    oq
    2.44
    
    2.34
    DetailsService
    2.28
    رة
    2.26
    !="
    2.24
    дық
    2.23
    oze
    2.22
    
    2.18
    اعد
    2.17
    Activations Density 0.012%

    No Known Activations