© 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. 15816
    Prev
    Next
    INDEX
    Explanations

    system calls

    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
    partum
    0.39
    
    0.39
    bc
    0.38
    ‑
    0.37
    ни
    0.37
    ніка
    0.36
    за
    0.36
    bcc
    0.36
    ž
    0.36
     dramatically
    0.35
    POSITIVE LOGITS
    ᚋ
    0.45
     센
    0.45
     clashes
    0.44
    ambahkan
    0.44
     इत्यादी
    0.44
     стоимо
    0.43
     এটাও
    0.42
     दायर
    0.42
     कां
    0.40
    }:=\
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.