© 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. 179637
    Prev
    Next
    INDEX
    Explanations

    rights, Party Services, security, logic

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

    understanding health sharing

    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
    ta
    0.60
    τ
    0.51
    ተኛ
    0.49
    σε
    0.48
    цтва
    0.48
    тая
    0.47
    ístico
    0.46
    superclass
    0.46
    ts
    0.46
    сне
    0.46
    POSITIVE LOGITS
    _
    0.47
     Librarian
    0.46
     secretariat
    0.44
     Municipal
    0.44
     referencing
    0.44
     reconstruct
    0.43
     appendices
    0.42
    级别的
    0.42
     Charitable
    0.42
     Munic
    0.42
    Activations Density 0.001%

    No Known Activations