© 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. 63446
    Prev
    Next
    INDEX
    Explanations

    falling in love

    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
    entamiento
    -0.84
    каун
    -0.83
    ziesz
    -0.81
     affidavit
    -0.80
     fluoride
    -0.79
    Chronicle
    -0.77
     FACILITIES
    -0.77
     downtown
    -0.77
     refineries
    -0.77
    ขึ้น
    -0.76
    POSITIVE LOGITS
     Falling
    1.37
     fall
    1.36
     falling
    1.34
    Falling
    1.30
    FALL
    1.27
     trap
    1.27
     Fall
    1.26
    fall
    1.26
     traps
    1.24
     FALL
    1.23
    Activations Density 0.020%

    No Known Activations