© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65824
    Prev
    Next
    INDEX
    Explanations

    allowed or not allowed

    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
     tatou
    -0.85
     yurt
    -0.83
    ঝ
    -0.82
    Enllaços
    -0.80
     roca
    -0.79
    یکس
    -0.79
     papillon
    -0.77
     juft
    -0.77
     inutile
    -0.77
    )}>
    -0.77
    POSITIVE LOGITS
     allowed
    7.28
     permitted
    5.94
    allowed
    5.69
    Allowed
    5.41
     Allowed
    5.22
     allowable
    4.81
    ALLOWED
    4.59
     permissible
    4.38
     ALLOWED
    4.31
    permitted
    4.22
    Activations Density 0.224%

    No Known Activations