© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13705
    Prev
    Next
    INDEX
    Explanations

    after four

    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
    <unused930>
    1.00
    <unused356>
    1.00
    catering
    0.97
     continueRoutine
    0.96
     tambien
    0.96
     elucid
    0.95
     RtlOverlay
    0.94
    <unused433>
    0.94
     catering
    0.93
    <unused1125>
    0.93
    POSITIVE LOGITS
     Even
    0.92
     Two
    0.84
     Key
    0.82
    0.80
     দেয়
    0.79
     Three
    0.78
     Paintings
    0.77
     Fear
    0.77
     Yourself
    0.76
     Danger
    0.76
    Activations Density 0.001%

    No Known Activations