© 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. 93521
    Prev
    Next
    INDEX
    Explanations

    javascript and php code

    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
    Masukkan
    -0.89
     ONLY
    -0.88
     منم
    -0.85
     إذا
    -0.81
     if
    -0.78
     Cannot
    -0.77
    Wasn
    -0.77
    を集
    -0.76
    evan
    -0.76
    ジナル
    -0.75
    POSITIVE LOGITS
    vales
    0.86
    dymo
    0.83
    ">!
    0.82
    доста
    0.81
     больше
    0.79
     condición
    0.79
    enthal
    0.78
    istream
    0.78
    both
    0.77
    }^\
    0.77
    Activations Density 0.010%

    No Known Activations