© 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. 77948
    Prev
    Next
    INDEX
    Explanations

    positive sentiment and praise

    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
    σκε
    -0.84
    gazione
    -0.82
     Opin
    -0.79
     opinion
    -0.75
    vény
    -0.71
    մ
    -0.71
     mourning
    -0.70
     invit
    -0.70
    టు
    -0.70
     indent
    -0.69
    POSITIVE LOGITS
     praise
    3.45
     praised
    2.73
    Praise
    2.53
    praise
    2.52
     Praise
    2.45
     praises
    2.42
     praising
    2.27
     lauded
    1.84
     heaped
    1.67
     PRA
    1.64
    Activations Density 0.021%

    No Known Activations