© 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. 20249
    Prev
    Next
    INDEX
    Explanations

    if... then conditions

    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
     ബെ
    0.43
     Bengaluru
    0.42
     duas
    0.42
    க்தி
    0.41
    %%%%
    0.40
     Кита
    0.40
    isasi
    0.40
     julg
    0.40
     Doğ
    0.39
     जोशी
    0.39
    POSITIVE LOGITS
     తిన
    0.46
     thisobject
    0.44
     ఇతర
    0.42
     nCurrent
    0.42
    rocytes
    0.41
     verhindert
    0.40
     externalities
    0.40
    esehen
    0.39
    )~
    0.39
     experiencing
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.