© 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. 232858
    Prev
    Next
    INDEX
    Explanations

    famous, learn, remember

    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
     latency
    0.52
    ਾ
    0.49
     對
    0.48
    ovalent
    0.48
     configuration
    0.48
     permutation
    0.46
     anx
    0.45
     synergy
    0.45
    ቆዳ
    0.44
    內
    0.44
    POSITIVE LOGITS
     знамени
    0.54
     berühm
    0.54
     apprendre
    0.54
     aprender
    0.52
     belajar
    0.52
     Lieblings
    0.52
     lernen
    0.50
     famosos
    0.50
     famosa
    0.48
     lembrar
    0.48
    Activations Density 0.001%

    No Known Activations