© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2401
    Prev
    Next
    INDEX
    Explanations

    unlike coal, nuclearunlike bull

    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_22_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
     बलराम
    0.89
     Monroe
    0.84
    GAD
    0.80
    溧
    0.78
     Kraus
    0.78
     रायपुर
    0.77
     Schubert
    0.76
     CLL
    0.73
     DSA
    0.72
    阮
    0.71
    POSITIVE LOGITS
     fire
    2.40
     flames
    2.36
     Fire
    2.23
     burning
    2.22
     fires
    2.22
    Fire
    2.18
     flame
    2.15
     Burning
    2.13
     burn
    2.12
     burns
    2.11
    Activations Density 0.858%

    No Known Activations