© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14496
    Prev
    Next
    INDEX
    Explanations

    Conditional outcomes and return values

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

    The neuron detects passive‐voice return statements describing missing or error conditions (e.g. “an error is returned” or “nothing is returned”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bises
    -1.18
    Característica
    -1.18
    PENUTUP
    -1.16
    ⻬
    -1.16
    Aprend
    -1.13
     ダイニング
    -1.09
    看了一眼
    -1.09
    雰囲
    -1.09
    ÍNDICE
    -1.07
    bilir
    -1.06
    POSITIVE LOGITS
     instead
    1.30
     or
    1.07
    ではなく
    1.01
     an
    0.99
     will
    0.96
     no
    0.95
    Ret
    0.94
     Juillet
    0.94
     neither
    0.94
    silien
    0.94
    Activations Density 0.046%

    No Known Activations