© 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. 22-GEMMASCOPE-RES-131K
    7. 34522
    Prev
    Next
    INDEX
    Explanations

    от, von, vom

    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
    <bos>
    -3.89
    this
    -2.25
    もあって
    -2.00
    不时
    -1.91
    相手の
    -1.91
     поскольку
    -1.88
    了几
    -1.84
    a
    -1.79
    それも
    -1.79
    子が
    -1.79
    POSITIVE LOGITS
    さぁ
    2.59
    えっ
    2.56
    あぁ
    2.36
    怱
    2.27
    ところに
    2.25
    って何
    2.22
    她
    2.16
     Then
    2.16
    に入れて
    2.14
     Therefore
    2.13
    Activations Density 0.003%

    No Known Activations