© 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. 173094
    Prev
    Next
    INDEX
    Explanations

    shower curtain

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

    words following numbers or specific prefixes

    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
    2
    0.59
    0
    0.52
    za
    0.51
    bare
    0.46
    hd
    0.45
    oke
    0.44
    live
    0.44
    build
    0.44
    ollar
    0.44
    ye
    0.44
    POSITIVE LOGITS
     সম্পর্
    0.52
    亅
    0.52
    绁
    0.52
    тят
    0.51
     representations
    0.51
    乆
    0.51
    撳
    0.50
    ευ
    0.49
    룀
    0.48
    መለ
    0.47
    Activations Density 0.000%

    No Known Activations