© 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. 22-GEMMASCOPE-RES-131K
    7. 128593
    Prev
    Next
    INDEX
    Explanations

    section headers

    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_22/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
    所で
    -1.55
    様な
    -1.54
     this
    -1.45
    ところに
    -1.42
    づけ
    -1.38
    おわりに
    -1.34
     olvidado
    -1.31
    無し
    -1.29
    をしました
    -1.27
     and
    -1.26
    POSITIVE LOGITS
    などが
    1.45
    もあって
    1.38
    だが
    1.28
    そういった
    1.28
    があり
    1.28
    しかし
    1.28
    UCIÓN
    1.27
    などは
    1.26
    がありますが
    1.26
    つまり
    1.25
    Activations Density 0.005%

    No Known Activations