© 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. 34-GEMMASCOPE-RES-131K
    7. 91850
    Prev
    Next
    INDEX
    Explanations

    clear or implied intent

    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
    ībā
    -1.07
    nappropriate
    -0.89
    .'</
    -0.87
    threat
    -0.85
    ###############
    -0.82
    baute
    -0.80
    innovative
    -0.77
    tigkeits
    -0.77
    cillary
    -0.76
    finally
    -0.75
    POSITIVE LOGITS
     intentional
    5.28
     deliberate
    5.00
     intentionally
    4.97
     deliberately
    4.88
     purposely
    4.09
     Deliber
    3.92
     purposefully
    3.83
     consciously
    3.81
    intention
    3.56
     purposeful
    3.50
    Activations Density 0.142%

    No Known Activations