© 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. 8915
    Prev
    Next
    INDEX
    Explanations

    cout <<

    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
    姗
    0.89
     గొప్ప
    0.88
    峥
    0.85
    ிற
    0.83
     epidemiology
    0.79
    处的
    0.78
     phrases
    0.78
     fingerprints
    0.77
    大力
    0.77
    꺾
    0.76
    POSITIVE LOGITS
    Sem
    1.27
    Semit
    1.18
     Sem
    1.10
    Semitic
    1.06
    sem
    1.06
    sema
    1.01
    LB
    0.99
     SEM
    0.98
    Demo
    0.97
    Cob
    0.96
    Activations Density 0.060%

    No Known Activations