© 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. 73498
    Prev
    Next
    INDEX
    Explanations

    brick veneer

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

    social connections and opportunities

    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
     gourmet
    0.51
    cadastro
    0.45
     steadily
    0.43
    ەکە
    0.42
    かかる
    0.42
    醫
    0.42
     delectable
    0.42
    ुरी
    0.41
     vem
    0.41
     salts
    0.40
    POSITIVE LOGITS
     отдела
    0.48
     অব্য
    0.48
     изначально
    0.46
     относя
    0.45
    rasında
    0.44
    PhysRev
    0.44
    UILLER
    0.43
     奥
    0.43
     প্রশিক্ষ
    0.42
    这款
    0.42
    Activations Density 0.000%

    No Known Activations