© 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. 15564
    Prev
    Next
    INDEX
    Explanations

    URL delimiter followed by content

    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
    ʇ
    1.11
     suono
    1.04
    ListenAnd
    0.99
     golpes
    0.96
     quién
    0.96
    அது
    0.95
    ⺀
    0.95
    ';"/>
    0.94
    Joke
    0.94
     cuestión
    0.94
    POSITIVE LOGITS
     early
    0.79
     coronary
    0.79
     Originally
    0.75
    belly
    0.74
    -
    0.72
     originally
    0.72
     architecture
    0.71
     assembly
    0.69
     originated
    0.69
     ingredients
    0.68
    Activations Density 0.001%

    No Known Activations