© 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. 13324
    Prev
    Next
    INDEX
    Explanations

    Musk and Putin statements

    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
    '
    2.30
     derrot
    2.27
    ’
    2.21
     đã
    2.09
     consiguió
    2.08
     berhasil
    2.07
    ʼ
    2.05
     selaku
    2.04
     sudah
    1.97
     frère
    1.96
    POSITIVE LOGITS
    intrinsic
    1.51
     intrinsic
    1.51
    integrity
    1.44
    tl
    1.42
     integrity
    1.32
     abnormality
    1.31
    variable
    1.29
    t
    1.28
    maturity
    1.28
    accessibility
    1.25
    Activations Density 0.023%

    No Known Activations