© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4467
    Prev
    Next
    INDEX
    Explanations

    yearning for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     khi
    0.87
    つ
    0.85
     when
    0.81
     Khi
    0.79
    when
    0.78
     जब
    0.76
    WHEN
    0.75
    Khi
    0.75
    chre
    0.73
    Ve
    0.72
    POSITIVE LOGITS
    anaconda
    0.74
    簷
    0.74
     دنبال
    0.72
    никами
    0.72
     хочется
    0.70
     Fractional
    0.70
    分页
    0.69
    abhuto
    0.69
    喟
    0.68
    னால்
    0.68
    Activations Density 0.141%

    No Known Activations