© 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. 13-GEMMASCOPE-2-RES-65K
    7. 2058
    Prev
    Next
    INDEX
    Explanations

    need to

    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_13_width_65k_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
    s
    1.30
    i
    1.27
    and
    1.26
    ib
    1.26
    or
    1.22
    r
    1.20
    -
    1.13
    ー
    1.13
    ture
    1.08
    I
    1.06
    POSITIVE LOGITS
     suffisamment
    2.04
     recourse
    2.03
     podido
    1.96
    𝘩
    1.84
     lepší
    1.83
     zostać
    1.82
     gotten
    1.82
     suficientes
    1.81
     været
    1.80
     passar
    1.79
    Activations Density 1.332%

    No Known Activations