© 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. 6146
    Prev
    Next
    INDEX
    Explanations

    when other conditions apply

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

    struggle with

    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
    OGRAPHY
    0.47
    ﾀ
    0.44
    תו
    0.44
    ITTLE
    0.44
    ਟ
    0.44
    NETT
    0.42
     নিজেও
    0.42
    ָ
    0.42
    ִי
    0.42
    רו
    0.42
    POSITIVE LOGITS
     سایر
    0.54
     pozosta
    0.47
     other
    0.45
     Otros
    0.45
     diğer
    0.45
     autres
    0.44
     anderen
    0.44
     remaining
    0.44
     innych
    0.43
     outras
    0.42
    Activations Density 0.002%

    No Known Activations