© 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. 10869
    Prev
    Next
    INDEX
    Explanations

    Anne Frank House, famine

    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
    LOADSTRING
    2.02
    ގ
    1.93
     UIFont
    1.90
    Ꭼ
    1.89
    لاین
    1.82
    முகம்
    1.80
    రం
    1.78
    តិ
    1.77
    ➙
    1.70
    ято
    1.67
    POSITIVE LOGITS
    y
    1.82
    л
    1.82
     ab
    1.75
    ing
    1.63
    ab
    1.60
     majesty
    1.58
    hit
    1.57
     Old
    1.56
    er
    1.54
    u
    1.51
    Activations Density 0.009%

    No Known Activations