© 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. 237600
    Prev
    Next
    INDEX
    Explanations

    paper articles

    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
    ي
    0.62
    ти
    0.57
    י
    0.53
     rupam
    0.51
    ி
    0.50
    쉼
    0.50
    𝘷
    0.49
    тическая
    0.49
    д
    0.49
    ი
    0.49
    POSITIVE LOGITS
     ephemeral
    0.46
     const
    0.43
     fragment
    0.42
     package
    0.41
     macroscopic
    0.41
     about
    0.41
     kel
    0.40
     housing
    0.40
     qt
    0.39
     submission
    0.39
    Activations Density 0.001%

    No Known Activations