© 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. 243483
    Prev
    Next
    INDEX
    Explanations

    common words followed by specific nouns

    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
    im
    0.57
    cn
    0.51
    ích
    0.50
    registers
    0.49
     യു
    0.49
    /).
    0.49
    ra
    0.48
    PTH
    0.47
     savaş
    0.46
    ]).
    0.46
    POSITIVE LOGITS
    Ар
    0.48
     hibernate
    0.46
    蛋白
    0.45
    ง
    0.45
    变为
    0.45
    粈
    0.43
     થાય
    0.42
    Це
    0.41
    ানু
    0.41
    졌다
    0.41
    Activations Density 0.001%

    No Known Activations