© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64029
    Prev
    Next
    INDEX
    Explanations

    rajasika, roop, raaz, rajyam, rajputana, raipur, rabdi

    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
    <bos>
    -0.93
    ですが
    -0.90
    と
    -0.85
     unut
    -0.82
    家の
    -0.81
    そして
    -0.80
    全新的
    -0.80
    s
    -0.80
    が
    -0.79
    や
    -0.79
    POSITIVE LOGITS
    為に
    1.03
    ところに
    1.00
    んですね
    0.98
    来週
    0.98
    様な
    0.98
    ようです
    0.96
    感じが
    0.94
    ようで
    0.94
    事で
    0.91
    댓
    0.91
    Activations Density 0.004%

    No Known Activations