© 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. 63766
    Prev
    Next
    INDEX
    Explanations

    affinity and persona

    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
     radically
    -0.75
     اخت
    -0.75
     greatly
    -0.73
     Cold
    -0.71
     enormously
    -0.70
     suitable
    -0.69
    LA
    -0.69
     rallado
    -0.69
     gereken
    -0.69
     mildly
    -0.68
    POSITIVE LOGITS
     Persona
    1.10
     Serif
    1.06
     Personas
    0.91
    persona
    0.86
     WIP
    0.84
     gimbal
    0.84
    Persona
    0.84
     persona
    0.83
     imperceptible
    0.82
     Affinity
    0.82
    Activations Density 0.053%

    No Known Activations