© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135343
    Prev
    Next
    INDEX
    Explanations

    Cinderella

    np_acts-logits-general · gemini-2.5-flash-lite

    hot air balloons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omicide
    0.43
     xã
    0.40
    ंसद
    0.40
     पार्
    0.38
     exter
    0.38
    痧
    0.38
    scient
    0.37
     Amal
    0.37
     parlament
    0.37
    肐
    0.37
    POSITIVE LOGITS
     Cinderella
    0.63
    inderella
    0.46
    FirebaseAuth
    0.45
     Title
    0.43
     Bucket
    0.43
     pumpkin
    0.41
    Titulo
    0.40
     Pumpkin
    0.39
    Title
    0.39
    ultra
    0.39
    Activations Density 0.016%

    No Known Activations