© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8504
    Prev
    Next
    INDEX
    Explanations

    multimodal

    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
    UDN
    1.02
    ライド
    0.99
    ندي
    0.98
     indietro
    0.98
    デックス
    0.97
     丶
    0.94
     Guarda
    0.92
    λοι
    0.92
    ǒu
    0.92
     tật
    0.89
    POSITIVE LOGITS
    ক
    0.87
    ла
    0.85
    lech
    0.85
    ీల
    0.82
    чі
    0.81
    แรง
    0.81
    हतक
    0.79
     feat
    0.78
    म्मा
    0.77
    inel
    0.77
    Activations Density 0.005%

    No Known Activations