© 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. 13-GEMMASCOPE-2-RES-16K
    7. 15550
    Prev
    Next
    INDEX
    Explanations

    daunting or overwhelming at first

    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_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
     наоборот
    1.09
     напротив
    0.97
     simply
    0.94
    鶴
    0.84
     bitten
    0.82
     otherwise
    0.82
    鵝
    0.82
    雲
    0.81
    相反
    0.81
     иначе
    0.79
    POSITIVE LOGITS
     internazionali
    1.09
     internacionales
    1.07
    kost
    1.05
     국제
    1.03
    HJ
    1.03
     collett
    1.03
    ចាំ
    1.02
    collective
    1.01
     modificaciones
    1.01
     internacional
    1.00
    Activations Density 0.188%

    No Known Activations