© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7689
    Prev
    Next
    INDEX
    Explanations

    almost imperceptible

    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
     Athe
    0.84
    兄弟
    0.82
    モ
    0.77
    (!
    0.76
     Mor
    0.75
    CONDUCT
    0.75
    RESULT
    0.75
    Mor
    0.74
    ма
    0.73
    ("*
    0.72
    POSITIVE LOGITS
    oken
    0.87
    ‬
    0.84
    apte
    0.82
    triggered
    0.82
    registered
    0.80
    ⟩
    0.80
    inden
    0.80
    〉
    0.80
     Ảnh
    0.80
     套
    0.79
    Activations Density 0.015%

    No Known Activations