© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41124
    Prev
    Next
    INDEX
    Explanations

    introducing similar ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     \
    -2.75
    }$
    -2.55
     живота
    -2.28
    戗
    -2.23
     następnie
    -2.23
    簠
    -2.22
    小声
    -2.19
     acht
    -2.19
    氿
    -2.19
     групп
    -2.17
    POSITIVE LOGITS
    呖
    2.86
    踽
    2.67
    ی
    2.64
    there
    2.64
    s
    2.63
    她
    2.58
    ‪.‬‬
    2.52
     didnt
    2.48
    亊
    2.45
     ,‬
    2.42
    Activations Density 0.001%

    No Known Activations