© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3204
    Prev
    Next
    INDEX
    Explanations

    i'm sorry,

    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
     posisi
    1.71
    䥑
    1.68
     jaringan
    1.66
     keber
    1.65
     responsáveis
    1.64
     setSnackbar
    1.62
    𒉈
    1.62
    𒍝
    1.60
    𒄷
    1.57
     manutenção
    1.56
    POSITIVE LOGITS
    that
    1.68
    like
    1.44
    .
    1.42
    knowing
    1.38
     that
    1.37
    when
    1.36
    think
    1.36
    thus
    1.35
     if
    1.33
     sort
    1.31
    Activations Density 0.161%

    No Known Activations