© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10404
    Prev
    Next
    INDEX
    Explanations

    conjunctions connecting concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     haue
    0.89
     tenha
    0.85
    provide
    0.82
     fulfil
    0.82
     puedas
    0.81
     nessa
    0.81
     fulfill
    0.80
    .[
    0.79
    Have
    0.78
    ciamo
    0.78
    POSITIVE LOGITS
     increased
    1.01
     coupled
    0.95
     negligible
    0.87
     penerapan
    0.87
     rampant
    0.86
     relentless
    0.86
     ferocious
    0.84
     insistence
    0.83
     fortsatt
    0.83
     repeated
    0.82
    Activations Density 0.117%

    No Known Activations