© 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. 34-GEMMASCOPE-RES-131K
    7. 99294
    Prev
    Next
    INDEX
    Explanations

    Objective-C, OpenGL, C++, Java

    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_34/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
    ocusing
    -0.87
     quickly
    -0.87
     miraculously
    -0.85
     seemingly
    -0.84
     strangely
    -0.80
     substantially
    -0.79
     ostensibly
    -0.79
     instantly
    -0.79
    6
    -0.79
     preceded
    -0.78
    POSITIVE LOGITS
    rya
    1.14
    yaa
    0.90
    estimable
    0.88
    llow
    0.88
    𝗣
    0.84
    ahh
    0.84
     incluse
    0.82
     sabias
    0.82
     Diskussion
    0.82
    Gaz
    0.82
    Activations Density 0.001%

    No Known Activations