© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8538
    Prev
    Next
    INDEX
    Explanations

    hey, i'm here

    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_13_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
     reversible
    0.94
    ᒧ
    0.93
     aliphatic
    0.91
     dissatisfaction
    0.89
     braids
    0.83
     scissors
    0.83
     oriented
    0.83
    ᇁ
    0.83
     replacement
    0.82
     unusable
    0.82
    POSITIVE LOGITS
     Your
    1.02
    めに
    0.96
    Putting
    0.86
     Sitting
    0.86
    你的
    0.85
     Around
    0.85
     Pierws
    0.84
    Sitting
    0.84
     Zijn
    0.83
    üğünüz
    0.83
    Activations Density 0.004%

    No Known Activations