© 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. 20078
    Prev
    Next
    INDEX
    Explanations

    end of phrases

    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
     they
    -1.28
    certainly
    -1.27
    wonderful
    -1.24
    completely
    -1.23
     superiore
    -1.23
     >",
    -1.23
     than
    -1.22
    辈子
    -1.19
    absolutely
    -1.18
    accro
    -1.18
    POSITIVE LOGITS
    end
    1.39
    ]}$
    1.38
    tiga
    1.36
    𓆸
    1.35
    衛門
    1.29
    ون
    1.27
    熊猫
    1.24
     Polícia
    1.23
     tarmac
    1.23
     云
    1.22
    Activations Density 0.079%

    No Known Activations