© 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. 13503
    Prev
    Next
    INDEX
    Explanations

    Top-p (Nucleus Sampling)

    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
    𝒆
    2.03
    er
    1.79
    𝒚
    1.73
    اء
    1.61
     мушка
    1.60
    yin
    1.58
    erit
    1.58
    y
    1.57
     lançamento
    1.54
     DISTINCT
    1.53
    POSITIVE LOGITS
     blowing
    1.77
     blew
    1.51
     assistance
    1.44
     evac
    1.37
     heading
    1.36
     bright
    1.35
    ilic
    1.34
     blow
    1.34
     awn
    1.33
     board
    1.31
    Activations Density 0.008%

    No Known Activations