© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65546
    Prev
    Next
    INDEX
    Explanations

    no confidence or censure

    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
    žit
    -0.83
    Quiet
    -0.78
    𝘳
    -0.72
    ウ
    -0.72
    jur
    -0.71
    ワイイ
    -0.71
     brąz
    -0.70
     électro
    -0.70
    wige
    -0.69
    propan
    -0.69
    POSITIVE LOGITS
     no
    1.89
     confidence
    1.88
    confidence
    1.66
     Confidence
    1.51
    No
    1.48
     censure
    1.48
    Confidence
    1.45
    no
    1.38
     No
    1.34
     NO
    1.27
    Activations Density 0.018%

    No Known Activations