© 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. 90294
    Prev
    Next
    INDEX
    Explanations

    Alabama Rot, walks like a duck

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

    cannot access real-time data

    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
     summation
    0.51
     correção
    0.50
     გვ
    0.49
     linearized
    0.48
     anormal
    0.48
     quê
    0.48
     gentile
    0.48
     Ś
    0.46
     remind
    0.45
     경우가
    0.45
    POSITIVE LOGITS
    Wednesday
    0.51
    THERE
    0.48
    सिटी
    0.48
    db
    0.46
    Architecture
    0.45
    के
    0.45
    ंडर
    0.45
    tx
    0.44
    ibre
    0.44
    Thursday
    0.44
    Activations Density 0.001%

    No Known Activations