© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1296
    Prev
    Next
    INDEX
    Explanations

    ad forgnarled and stainedpeg intonar followed by led

    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
    𝙮
    1.44
     Але
    1.35
    锛
    1.34
     rameaux
    1.29
     Retour
    1.28
     cardamom
    1.26
    Telefono
    1.25
    טו
    1.25
    𝘆
    1.23
    ('%
    1.22
    POSITIVE LOGITS
     As
    1.19
     For
    1.14
    ような
    1.12
     individual
    1.09
     individuals
    1.07
     govern
    1.06
    ubs
    1.06
     ''){
    1.04
     ಪ್ರ
    1.04
     ස
    1.03
    Activations Density 0.517%

    No Known Activations