© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 10555
    Prev
    Next
    INDEX
    Explanations

    appear to sound like

    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_22_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
    ٩
    0.89
    ❤
    0.88
     nineteen
    0.87
    👪
    0.81
     ৩৪
    0.81
     council
    0.80
     babies
    0.79
     languages
    0.79
     ❤
    0.78
     seperate
    0.78
    POSITIVE LOGITS
    ന്യൂ
    0.85
    égard
    0.80
    ovka
    0.80
     spoiling
    0.78
    rach
    0.77
     fame
    0.77
     fong
    0.76
     rng
    0.75
    פון
    0.74
    conductivity
    0.73
    Activations Density 0.151%

    No Known Activations