© 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. 255259
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    癮
    0.50
    edizione
    0.47
     behov
    0.46
    ulata
    0.46
    변경된
    0.46
     benötigen
    0.45
    gette
    0.45
    グ
    0.45
    ateur
    0.44
    lake
    0.44
    POSITIVE LOGITS
     Steering
    0.57
     Commandant
    0.56
     Computation
    0.54
     Correlation
    0.51
     s
    0.49
     Steep
    0.49
     c
    0.48
     Cardinal
    0.48
     or
    0.47
     sulfur
    0.47
    Activations Density 0.000%

    No Known Activations