© 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. 257154
    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
     consolidating
    0.44
    5
    0.42
     পরবর্তীতে
    0.42
     freshmen
    0.40
     éxitos
    0.39
     MSM
    0.38
     articulating
    0.38
     longitudinale
    0.38
     親
    0.38
     семья
    0.38
    POSITIVE LOGITS
    Texto
    0.41
    RequestId
    0.39
    }=-\
    0.38
    itext
    0.38
    হয়
    0.38
    ariş
    0.37
     deterioro
    0.37
    રિ
    0.37
    స్క
    0.36
    வைக்
    0.36
    Activations Density 0.003%

    No Known Activations