© 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. 14934
    Prev
    Next
    INDEX
    Explanations

    people and someone

    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
     who
    2.19
    innen
    2.10
    folk
    1.98
    mith
    1.94
    '
    1.94
    ’
    1.88
    ponsored
    1.85
     and
    1.81
    hips
    1.81
    '.
    1.77
    POSITIVE LOGITS
    𝐚
    2.51
     romanzo
    2.32
    Curso
    2.25
    ו
    2.24
     prazo
    2.21
     vettore
    2.16
     paralelo
    2.06
     Ereign
    2.06
    𝐎
    2.05
    𒌌
    2.05
    Activations Density 0.174%

    No Known Activations