© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 158126
    Prev
    Next
    INDEX
    Explanations

    URLs and external references

    np_acts-logits-general · gemini-2.5-flash-lite

    your ideas and observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     discouraging
    0.45
     PGA
    0.44
     naut
    0.43
     hampers
    0.43
    中
    0.43
    B
    0.42
    は
    0.42
     traditional
    0.42
     randon
    0.42
    क
    0.41
    POSITIVE LOGITS
    zeichnis
    0.50
    rvats
    0.47
    kość
    0.47
    žite
    0.47
     कांस
    0.47
     Tjiwarl
    0.47
    usstsein
    0.46
     মিলিয়ন
    0.46
     tumbuh
    0.46
    ϑ
    0.46
    Activations Density 0.000%

    No Known Activations