© 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. 28976
    Prev
    Next
    INDEX
    Explanations

    engineers and product developers

    np_acts-logits-general · gemini-2.5-flash-lite

    LLMs limitations

    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
    Pren
    0.49
     wszyst
    0.45
     Holton
    0.45
    გნ
    0.43
     Aunque
    0.42
    ,/*
    0.42
     וי
    0.42
     następnie
    0.42
     lanjut
    0.42
     выходит
    0.42
    POSITIVE LOGITS
     ఆది
    0.49
    system
    0.49
    ças
    0.49
    iterable
    0.46
    ie
    0.46
    ki
    0.44
    mont
    0.43
    ស្ថានភាព
    0.43
    ü
    0.43
    endpoint
    0.42
    Activations Density 0.000%

    No Known Activations