© 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. 204466
    Prev
    Next
    INDEX
    Explanations

    words following "in"

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

    feeling overwhelmed with

    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
     magnetization
    0.44
    Stefan
    0.44
    ]，
    0.43
    我們的
    0.41
    我们的
    0.41
    这
    0.41
    刂
    0.41
    橄
    0.41
     preliminary
    0.40
    已知
    0.40
    POSITIVE LOGITS
    y
    0.44
     fancy
    0.44
    ނީ
    0.42
    💻
    0.42
     НЕ
    0.42
     critérios
    0.41
    itabbo
    0.41
     بقى
    0.40
     critères
    0.40
     ڈاکٹر
    0.40
    Activations Density 0.001%

    No Known Activations