© 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. 212886
    Prev
    Next
    INDEX
    Explanations

    setting parameters or stating facts

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

    specific labels or entities

    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
    Anagram
    0.52
    酮
    0.50
    幷
    0.49
    Estimation
    0.48
    𝓑
    0.47
    Entertainment
    0.46
    Beyblade
    0.46
    Debit
    0.46
    يتر
    0.46
    مل
    0.46
    POSITIVE LOGITS
    ’
    0.56
     devel
    0.51
     create
    0.50
     confirm
    0.49
     aud
    0.48
     xi
    0.48
     decisively
    0.48
     examined
    0.46
     firm
    0.46
     vou
    0.46
    Activations Density 0.000%

    No Known Activations